The DOI matches its Crossref record; 280 of the 282 references it cites were found in a registry or an index, and 2 are not checked yet; none of the 393 sources its claims cite is checked for support yet.
Building machines that learn and think like people
Open accessAbstract
Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn and how they learn it. Specifically, we argue that these machines should (1) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (2) ground learning in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and (3) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes toward these goals that can combine the strengths of recent neural network advances with more structured cognitive models.
Checked 2026-10-05 · 2 references not checked yet
Overview
AI snapshot
Written from a shortened version of the paper’s full text (it is longer than we read).
TL;DR
The paper argues that deep learning systems can match or exceed human performance on some pattern-recognition tasks but still lack key ingredients of human-like learning and thought, especially causal model building, intuitive physics and psychology, compositionality, and learning-to-learn. It uses handwritten character learning and the Atari game Frostbite as challenge problems to show where current systems fall short and to propose routes toward more human-like machines.
Key findings
- The DQN needed about 924 hours of unique experience per Atari game, roughly 500 times the approximately 2 hours given to a professional gamer, and achieved less than 10% of human-level Frostbite performance in a controlled test; later variants reached 83% and 172% of the expert score but still required far more experience. In the authors’ informal play, after watching about 2 minutes of expert video, they reached expert-comparable Frostbite scores within 15–20 minutes of practice.
- On handwritten characters, deep convolutional networks approach human error on MNIST at 0.2%, but one-shot learning differs sharply: Bayesian program learning achieved human-level one-shot classification and generation after pretraining on five alphabets (about 150 character types), whereas deep ConvNets had 23% error versus 4% for humans with five alphabets, and 30% error with 30 alphabets.
- AlphaGo was initially trained on 28.4 million positions from 160,000 human games and then improved through 30 million self-play games, while Lee Sedol is estimated to have played around 50,000 games in his life; the paper uses this contrast to argue that human-like understanding and flexible generalization remain distinct from benchmark performance.
- The paper proposes core ingredients for human-like intelligence: intuitive physics, intuitive psychology, compositionality, causality, learning-to-learn, and fast approximate inference or model-free support for slower model-based reasoning.
Methods
- Conceptual review and synthesis drawing on cognitive science, developmental psychology, and artificial intelligence; no new formal experiment is reported.
- Two running challenge problems are used: the Characters Challenge for one-shot handwritten character concept learning, and the Frostbite Challenge for deep reinforcement learning control.
- The analysis contrasts pattern recognition with model building, reviews evidence on human learning and machine learning, and proposes integration routes; it also includes informal author play of Frostbite after watching expert videos.
Limitations
- Stated: the ingredient list is not intended to be complete; language is acknowledged as essential but not developed; the authors remain agnostic about whether the ingredients are innate or learned; and the focus is on neural networks, with probabilistic machine learning largely beyond scope.
- Evident: there is no controlled empirical study; the Frostbite human comparison relies on informal author play and prior experience; and the challenge comparisons may be confounded by humans’ extensive prior knowledge, which the authors acknowledge but do not fully resolve.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
267 Not checked yet · 224 Own interpretation · 128 No basis given · 9 Own result
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Humans, after playing just a small number of games over a span of minutes, can understand the game and its goals well enough to perform better than deep networks do after almost a thousand hours of experience”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If humans are able to first watch an expert playing for a few minutes, they can learn even faster”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The learned DQN network is also rather inflexible to changes in its inputs and goals”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Random play achieves a score of 65.2”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“after watching videos of expert play on YouTube for just 2 minutes, we found that we were able to reach scores comparable to or better than the human expert reported in Mnih et al. (2015) after at most 15 to 20 minutes of total practice”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
What the sources say
- Not checked yetcites Mnih et al. (2015)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“they can learn to play better than chance within a few minutes”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“in which people substantially outperform current DQN approaches”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“even non-professional humans can grasp the basics of the game after just a few minutes of play”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“a physics-engine reconstruction of a tower of wooden blocks from the game Jenga can be used to predict whether (and how) a tower will fall, finding close quantitative fits to how adults make these predictions”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
What the sources say
- Not checked yetcites Battaglia et al. 2013
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It has been shown to generalize, but also only in limited ways (e.g., from towers of two and three cubes to towers of four cubes)”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 156
- Probably not a substantial claim. 166
- The quote only partly states this claim. 1
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Even the best deep networks learn gradually over many thousands of game episodes, take a long time to reach good performance, and are locked into particular input and goal patterns”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
In the paper
“We recently reported progress on this challenge using probabilistic program induction (Lake et al. 2015a) (see Glossary in Table 1), yet aspects of the full human cognitive ability remain out of reach.”
§ Building machines that learn and think like people > 3.1. The Characters Challenge
What the sources say
- Not checked yetcites Lake et al. 2015a
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Human and PhysNet confidence were also correlated across towers, although not as strongly as for the approximate probabilistic simulation models and experiments of Battaglia et al. (2013)”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
What the sources say
- Not checked yetcites Lerer et al. 2016
- Not checked yetcites Battaglia et al. 2013
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Impressively, PhysNet generalized to simple real images of block towers, matching human performance on these images, meanwhile exceeding human performance on synthetic images”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
What the sources say
- Not checked yetcites Lerer et al. 2016
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Causal knowledge has also been shown to influence how people learn new concepts; providing a learner with different types of causal knowledge changes how he or she learns and generalizes.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Learning models of this form allows BPL to perform a challenging one-shot classification task at human-level performance (Fig. 1A-i) and to outperform current deep learning models such as convolutional networks (Koch et al. 2015).”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Koch et al. 2015
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“In many cases, the network gets the key objects in a scene correct, but fails to understand the physical forces at work, the mental states of the people, or the causal relationships between the objects.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Although it synthesizes impressive examples of handwriting in various styles, it requires a large training corpus and has not been applied to other tasks.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Graves 2014
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“But anecdotally, we find that humans can still reach these scores with a few minutes of practice, requiring far less experience than the DQNs.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although transfer learning and multitask learning are already important themes across AI, and in deep learning in particular, they have not yet led to systems that learn new tasks as rapidly and flexibly as humans do.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“With this level of pre-training, current neural networks perform much worse on classification and have not even attempted generation; they are still far from solving the Characters Challenge.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Deep reinforcement learning systems for playing Atari games have had some impressive successes in transfer learning, but they still have not come close to learning to play new games as quickly as humans can.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“An attentional window is only a crude approximation of the true causal process of drawing with a pen, and in Rezende et al. (2016) the attentional window is not pen-like at all, although a more accurate pen model could be incorporated.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Rezende et al. 2016
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Although it outperforms existing methods on various causal prediction tasks, it is unclear how to apply the approach to inferring rich hierarchies of latent causal variables, as needed for the Frostbite Challenge and especially the Characters Challenge.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Lopez-Paz et al. 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Similarly, as described in the Characters Challenge, people can quickly infer motor programs to draw a new character in a similarly guided processes.”
§ Building machines that learn and think like people > 4.3. Thinking Fast
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“The model demonstrates an impressive ability to make plausible generalizations that go beyond the training examples, yet it generalizes too broadly in other cases, in ways that are not especially human-like.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Rezende et al. 2016
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Many seemingly well-accepted ideas regarding neural computation are in fact biologically dubious, or uncertain at best”
§ Building machines that learn and think like people > 5.2. Biological plausibility suggests theories of intelligence should start with neural networks
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Deep reinforcement learning is only just starting to address intrinsically motivated learning (Kulkarni et al. 2016;Mohamed & Rezende 2015).”
§ Building machines that learn and think like people > 4.3.2. Model-based and model-free reinforcement
What the sources say
- Not checked yetcites Kulkarni et al. 2016
- Not checked yetcites Mohamed & Rezende 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“it is widely recognized that neural networks are far from implementing human language abilities.”
§ Building machines that learn and think like people > 5.3. Language is essential for human intelligence. Why is
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Exploration and creative innovation in the space of network architectures have not yet been made algorithmic.”
§ Building machines that learn and think like people > 5.1. Comparing the learning speeds of humans and neural networks on specific tasks is not meaningful, because humans have extensive prior experience
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although neuroscientists have not found any mechanisms for implementing backpropagation in the brain, neither have they produced definitive evidence against it.”
§ Building machines that learn and think like people > 5.2. Biological plausibility suggests theories of intelligence should start with neural networks
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Deep learning systems have not yet shown they can work with these representations, but they have demonstrated the surprising effectiveness of gradient descent in large models with high-dimensional parameter spaces.”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
In the paper
“these abilities elude even the best deep neural networks for character recognition (Ciresan et al. 2012), which are trained on many examples of each concept and do not flexibly generalize to new tasks.”
§ Building machines that learn and think like people > 6. Looking forward
What the sources say
- Not checked yetcites Ciresan et al. 2012
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“current algorithms are still better at recognizing objects than understanding scenes, often getting the key objects right but their causal relationships wrong (Fig. 6).”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
What the sources say
- Not checked yetcites Fig. 6
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“neural networks do engage in model building, which is implicit, and cannot be dissociated from the learning process”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
What the sources say
- Not checked yetcites Caglar & Hanson 2016
- Not checked yetcites Cleeremans 1993
- Not checked yetcites Hanson & Burr 1990
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Lee has probably played around 50,000 games in his entire life.”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“the DNC has been applied to solving block puzzles and finding paths between nodes in a graph after memorizing the graph.”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
What the sources say
- Not checked yetcites Graves et al. 2016
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“people learn from fewer data and generalize in richer and more flexible ways.”
§ Building machines that learn and think like people > 6. Looking forward
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“AlphaGo is initially trained on 28.4 million positions and moves from 160,000 unique games played by human experts; it then improves through reinforcement learning, playing 30 million more games against itself.”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
What the sources say
- Not checked yetcites Silver et al. 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“AI can also draw on observations of expert players, but requires substantially greater input to achieve similar levels of performance.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“The supervisory system appears to perform a variety of functions, such as goal generation (to create one's own goals and to function in real domains outside of the laboratory), strategy generation and evaluation (to create and evaluate potential strategies that might achieve goals), monitoring (to detect when one's goals are frustrated and to thereby trigger generation of new plans/strategies or”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
What the sources say
- Not checked yetcites Shallice & Cooper [2011]
- Not checked yetcites Fox et al. [2013]
- Not checked yetcites Cooper [2016]
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“A large collection of research comparing the development of children's understanding of false belief in the United States, China, and Iran indicates that although typically developing children in all cultures show an improvement in false belief understanding over the course of ontogeny, the timing of this improvement differs widely-and such variability is potentially related to different socioc”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
What the sources say
- Not checked yetcites Davoodi et al. 2016
- Not checked yetcites Liu et al. 2008
- Not checked yetcites Shahaeian et al. 2011
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Conversely, the differences between the causal processes that generate a cat and those that generate a dog are understood imperfectly, even by experts in developmental biology, and hardly at all by laypeople.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although contemporary DL approaches to, say, learning and playing Atari games undoubtedly employ psychologically unrealistic training regimes, and are undoubtedly inflexible with respect to changes to the reward/ goal structure, to fixate on these limitations overlooks the promise of such approaches.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Valence direction and magnitude often depend on the learner machine's disposition toward response priming/contagion, social facilitation, incentive motivation, and local/stimulus enhancement of observable demonstrator behavior”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“the shape of the learning curves for single-layer NNs and for multilayered DLs are qualitatively different, with the former fitting a negative exponential function (“associative”) and the latter fitting a hyperbolic function (“accumulative”)”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
What the sources say
- Not checked yetcites Caglar & Hanson 2016
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“There is no evidence that humans routinely generate comparably detailed traces or even that they are capable of doing so.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
In the paper
“Human subjects often make errors in predicting the behavior of a balance beam (Siegler 1976), and most people find the behavior of a gyroscope mystifying.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
What the sources say
- Not checked yetcites Siegler 1976
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Yet even children can readily distinguish dogs from cats.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Birds build species-typical nests they have never seen built, improving over time, and apes know a branch that is too weak to hold them.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“Decades of successful models have been built for many aspects of intuitive physics, and such models have also been used to ground scientific and engineering reasoning (Forbus 2011).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Forbus 2011
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“This has enabled Companions to learn causal models via reading natural language texts, thereby improving their performance in a complex strategy game (McFate et al. 2014).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites McFate et al. 2014
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“The studies by Dietvorst et al. (2015;2016;see Hutson 2017) suggest that people not only tend to distrust AIs, but also want to exert control, and hence responsibility, over the results such AIs deliver.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Dietvorst et al. (2015
- Not checked yetcites [2016]
- Not checked yetcites Hutson 2017
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“One's knowledge of the state of another agent's mind and one's ability to predict their action are necessarily extremely limited; nonetheless, powerful psychological reasoning can be carried out.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“For example, physicists asked to solve a novel problem spontaneously use analogies to known systems (Clement 1988), and studies of working microbiology laboratories reveal that frequent use of analogies is a major determinant of success (Dunbar 1995).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Clement 1988
- Not checked yetcites Dunbar 1995
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For example, if you see a person pick up a telephone and dial, it is a good guess that they he or she is planning to talk to someone.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Analogical processes support children's learning of physical science (Chen & Klahr 1999;Gentner et al. 2016) and mathematics (Carey 2009;Mix 1999;Richland & Simms 2015).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Chen & Klahr 1999
- Not checked yetcites Gentner et al. 2016
- Not checked yetcites Carey 2009
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We found that even simple changes to the visual environment (as insignificant as changing the brightness) dramatically and adversely affect the performance of the algorithm, whereas humans are not affected by such perturbations at all.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we see model building as the hallmark of human-level learning, or explaining observed data through the construction of causal models of the world”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“People can learn to recognize a new handwritten character from a single example (Fig. 1A-i), allowing them to discriminate between novel instances drawn by other people and similar looking non-instances (Lake et al. 2015a;Miller et al. 2000).”
§ Building machines that learn and think like people > 3.1. The Characters Challenge
What the sources say
- Not checked yetcites Lake et al. 2015a
- Not checked yetcites Miller et al. 2000
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Equipped with these general principles, people can learn more quickly and make more accurate predictions.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By contrast, model-free reinforcement learning algorithms, such as current instantiations of deep reinforcement learning, support fast control, but at the cost of inflexibility and possibly accuracy.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A primary job of learning is to extend and enrich these models and to build analogous causally structured theories of other domains.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“The resurgence of recent interest in neural networks, more commonly referred to as”
§ Building machines that learn and think like people > 2. Cognitive and neural inspiration in artificial intelligence
What the sources say
- Not checked yetcites LeCun et al. [2015]
- Not checked yetcites Schmidhuber [2015]
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Now, the leading approaches to speech recognition are fully neural network systems (Graves et al. 2013;Hannun et al. 2014).”
§ Building machines that learn and think like people > 1. Introduction
What the sources say
- Not checked yetcites Graves et al. 2013
- Not checked yetcites Hannun et al. 2014
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“where the high-level feature representations of these convolutional nets have also been used to predict patterns of neural response in human and macaque IT cortex (Khaligh-Razavi & Kriegeskorte 2014;Kriegeskorte 2015;Yamins et al. 2014), as well as human typicality ratings (Lake et al. 2015b) and similarity ratings (Peterson et al. 2016) for images of common objects.”
§ Building machines that learn and think like people > 2. Cognitive and neural inspiration in artificial intelligence
What the sources say
- Not checked yetcites Khaligh-Razavi & Kriegeskorte 2014
- Not checked yetcites Kriegeskorte 2015
- Not checked yetcites Yamins et al. 2014
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This knowledge is often richly organized and theory-like in structure, capable of the graded inferences and productive capacities characteristic of human thought.”
§ Building machines that learn and think like people > 3. Challenges for building more human-like machines
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Also, the earlier an ingredient is present, the more likely it is to be foundational to later development and learning.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Compared with state-of-the-art algorithms in machine learning, human learning is distinguished by its richness and its efficiency.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
- Rests on an assumption: Children possess the ability and desire to uncover underlying causes of sparsely observed events and use that knowledge to go beyond limited data.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, planning in complex models is cumbersome and slow, making the speedaccuracy trade-off unfavorable for real-time control.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
- Rests on an assumption: Once a causal model of a task is learned, humans can use the model to plan action sequences that maximize future reward.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the claim that a mind is a collection of general-purpose neural networks with few initial constraints is rather extreme in contemporary cognitive science.”
§ Building machines that learn and think like people > 3. Challenges for building more human-like machines
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“finding that deep learning models have yet to incorporate many of them, and so may be solving some problems in different ways than people do.”
§ Building machines that learn and think like people > 1. Introduction
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: People are better than machines at solving a range of difficult computational problems including concept learning, scene understanding, language acquisition, language understanding, and speech recognition.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Handwritten character recognition is also simpler than more general forms of object recognition; the object of interest is two-dimensional, separated from the background, and usually unoccluded.”
§ Building machines that learn and think like people > 3.1. The Characters Challenge
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Infants understand that other people have mental states like goals and beliefs, and this understanding strongly constrains their learning and predictions.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
What the sources say
- Not checked yetcites Wellman & Gelman [1992]
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“With a large amount of training data available, many algorithms achieve respectable performance, including Knearest neighbors (5% test error), support vector machines (about 1% test error), and convolutional neural networks (below 1% test error [LeCun et al. 1998]).”
§ Building machines that learn and think like people > 3.1. The Characters Challenge
What the sources say
- Not checked yetcites LeCun et al. 1998
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“A different picture has emerged that highlights the importance of early inductive biases, including core concepts such as number, space, agency, and objects, as well as powerful learning algorithms that rely on prior knowledge to extract knowledge from small amounts of training data.”
§ Building machines that learn and think like people > 3. Challenges for building more human-like machines
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If an ingredient is present early in development, it is certainly active and available well before a child or adult would attempt to learn the types of tasks discussed in this paper.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Some of the original work done under the banner of PDP (Rumelhart et al. 1986b) is closer to model building than pattern recognition, whereas the recent large-scale discriminative deep learning systems more purely exemplify pattern recognition (see Bottou [2014] for a related discussion).”
§ Building machines that learn and think like people > 2. Cognitive and neural inspiration in artificial intelligence
What the sources say
- Not checked yetcites Rumelhart et al. 1986b
- Not checked yetcites Bottou [2014]
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“In the years since, ConvNets continue to dominate, recently approaching human-level performance on some object recognition benchmarks (He et al. 2016;Russakovsky et al. 2015;Szegedy et al. 2014).”
§ Building machines that learn and think like people > 1. Introduction
What the sources say
- Not checked yetcites He et al. 2016
- Not checked yetcites Russakovsky et al. 2015
- Not checked yetcites Szegedy et al. 2014
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“There are at least two important differences: people learn from fewer examples and they learn richer representations, a comparison true for both learning handwritten characters and for learning more general classes of objects (Fig. 1).”
§ Building machines that learn and think like people > 3.1. The Characters Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: People are better than machines at solving a range of difficult computational problems including concept learning, scene understanding, language acquisition, language understanding, and speech recognition.
In the paper
“For example, infants know that objects will persist over time and that they are solid and coherent.”
§ Building machines that learn and think like people > 1.2. Overview of the key ideas
What the sources say
- Not checked yetcites Wellman & Gelman [1992]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The network embodies the strongly empiricist approach characteristic of most connectionist models: very little is built into the network apart from the assumptions about image structure inherent in convolutional networks, so the network has to essentially learn a visual and conceptual system from scratch for each new game.”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The differences between the human and machine learning curves suggest that they may be learning different kinds of knowledge, using different learning mechanisms, or both.”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Human learners fundamentally take on different learning tasks than today's neural networks”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“More recent variants of the DQN perform better, and can even outperform the human tester (Schaul et al. 2016;Stadie et al. 2016;van Hasselt et al. 2016;Wang et al. 2016), reaching 83% of the professional gamer's score by incorporating smarter experience replay (Schaul et al. 2016), and 172% by using smarter replay and more efficient parameter sharing (Wang et al. 2016)”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
What the sources say
- Not checked yetcites Schaul et al. 2016
- Not checked yetcites Wang et al. 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“More recent work has shown how these game-specific networks can share visual features (Rusu et al. 2016) or be used to train a multitask network (Parisotto et al. 2016), achieving modest benefits of transfer when learning to play new games.”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
What the sources say
- Not checked yetcites Rusu et al. 2016
- Not checked yetcites Parisotto et al. 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“By the time a child or an adult is picking up a new character or learning how to play Frostbite, he or she is armed with extensive real-world experience that deep learning systems do not benefit from”
§ Building machines that learn and think like people > 4. Core ingredients of human intelligence
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“In addition to recognizing new examples, people can also generate new examples (Fig. 1A-ii), parse a character into its most important parts and relations (Fig. 1A-iii) (Lake et al. 2012), and generate new characters given a small set of related characters (Fig. 1A-iv).”
§ Building machines that learn and think like people > 3.1. The Characters Challenge
What the sources say
- Not checked yetcites Lake et al. 2012
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“People never start completely from scratch, or even close to”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Furthermore, people can efficiently integrate across multiple examples of a character to infer which have optional elements, such as the horizontal cross-bar in '7's, combining different variants of the same character into a single coherent representation.”
§ Building machines that learn and think like people > 3.1. The Characters Challenge
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
- Rests on an assumption: People can integrate across multiple examples of a character to infer optional elements, such as the cross-bar in '7's, and combine variants into a single coherent representation.
In the paper
“The DQN was a significant advance in reinforcement learning, showing that a single algorithm can learn to play a wide variety of complex tasks.”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
What the sources say
- Not checked yetcites Mnih et al. 2015
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“people understand enough to invent or accept new goals, generalize over changes to the input, and explain the game to others”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“recent experiments showing that children seek out new data to distinguish between hypotheses, isolate variables, test causal hypotheses, make use of the data-generating process in drawing conclusions, and learn selectively from others”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
What the sources say
- Not checked yetcites Cook et al. 2011
- Not checked yetcites Gweon et al. 2010
- Not checked yetcites Schulz et al. 2007
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“These domains include number (numerical and set operations), space (geometry and navigation), physics (inanimate objects and mechanics), and psychology (agents and groups)”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although both people and models represent characters as a sequence of pen strokes and relations, people have a far richer repertoire of structural relations between strokes.”
§ Building machines that learn and think like people > 3.1. The Characters Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“important physical concepts are present at ages far earlier than when a child or adult learns to play Frostbite, suggesting these resources may be used for solving this and many everyday physics-related tasks”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“people can learn models and use them for arbitrary new tasks and goals”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the key claim is that these ingredients play an active and important role in producing human-like learning and thought, in ways contemporary machine learning has yet to capture”
§ Building machines that learn and think like people > 4. Core ingredients of human intelligence
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
- Rests on an assumption: The core ingredients of human intelligence are not present in most current learning-based AI systems, and not all of them are present together.
In the paper
“The learning curve for the model of Wang et al. (2016) shows performance is approximately 44% after 200 hours, 8% after 100 hours, and less than 2% after 5 hours (which is close to random play, approximately 1.5%).”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
What the sources say
- Not checked yetcites Wang et al. 2016
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“The DQN was trained on 200 million frames from each of the games, which equates to approximately 924 hours of game time (about 38 days), or almost 500 times as much experience as the human received.”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
What the sources say
- Not checked yetcites Mnih et al. 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Although neural networks can learn multiple mappings or tasks with the same set of stimuliadapting their outputs depending on a specified goalthese models require substantial training or reconfiguration to add new tasks”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
What the sources say
- Not checked yetcites Collins & Frank 2013
- Not checked yetcites Eliasmith et al. 2012
- Not checked yetcites Rougier et al. 2005
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“In Mnih et al. (2015), the network architecture and hyper-parameters were fixed, but the network was trained anew for each game, meaning the visual system and the policy are highly specialized for the games it was trained on.”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
What the sources say
- Not checked yetcites Mnih et al. 2015
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“together the domains are thought to be shared cross-culturally and partly with non-human animals”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Certainly, the core ingredients are enriched by this experience, and some may even be a product of the experience itself”
§ Building machines that learn and think like people > 4. Core ingredients of human intelligence
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“Liquids, for example, are expected to go through barriers, while solid objects cannot”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
What the sources say
- Not checked yetcites Hespos et al. 2009
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Young infants believe objects should move along smooth paths, not wink in and out of existence, not inter-penetrate and not act at a distance”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“it is clear that these abilities are early emerging and play an important role in human learning and thought”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Intuitive psychology is another early-emerging ability with an important influence on human learning and thought”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“An explicit agent representation can predict how such an agent will be helpful in new circumstances, whereas a bottom-up pixel-based representation is likely to struggle”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In contrast, people require far less experience to perform any particular task, and can generalize to many novel judgments and complex scenes with no new training required”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“it seems to us that any full formal account of intuitive psychological reasoning needs to include representations of agency, goals, efficiency, and reciprocal relations”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Importantly, unlike in intuitive physics, simulation-based reasoning in intuitive psychology can be nested recursively to understand social interactions”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Such cues are often sufficient but not necessary for the detection of agency”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, these networks do not attempt to work with complex scenes as input, or a wide range of scenarios and judgments as in Figure 4”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the DQN probably does not parse a Frostbite screenshot in terms of stable objects or sprites moving according to the rules of intuitive physics”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“According to this hypothesis, people reconstruct a perceptual scene using internal representations of the objects and their physically relevant properties (such as mass, elasticity, and surface friction) and forces acting on objects (such as gravity, friction, or collision impulses)”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This”
§ Building machines that learn and think like people > 3.2. The Frostbite Challenge
plaindirect- Asserted: fails — The authors may not put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The authors may not put it forward as true. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By simulating these planning processes, people can predict what agents might do next, or use inverse reasoning from observing a series of actions to infer the utilities and beliefs of agents in a scene”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“these algorithms implement learning as a process of gradual adjustment of connection strengths”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For supervised learning, the updates are usually aimed at improving the algorithm's pattern recognition capabilities”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These models formalize explicitly mentalistic concepts such as”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Relative to physical ground truth, the intuitive physical state representation is approximate and probabilistic, and oversimplified and incomplete in many ways”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“infants also expect agents to act contingently and reciprocally, to have goals, and to take efficient actions toward those goals subject to constraints”
§ Building machines that learn and think like people > 4.1. Developmental start-up software
What the sources say
- Not checked yetcites Csibra 2008
- Not checked yetcites Csibra et al. 2003
- Not checked yetcites Spelke & Kinzler 2007
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Relating data to their causal source provides strong priors for perception and learning, as well as a richer basis for generalizing in new ways and to new tasks.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“There are also domains for which machine learners outperform human learners, such as combing through financial or weather data”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Beyond classification, concepts support prediction (Murphy & Ross 1994;Rips 1975), action (Barsalou 1983), communication (Markman & Makin 1998), imagination (Jern & Kemp 2013;Ward 1994), explanation (Lombrozo 2009;Williams & Lombrozo 2010), and composition (Murphy 1988;Osherson & Smith 1981)”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Murphy & Ross 1994
- Not checked yetcites Barsalou 1983
- Not checked yetcites Markman & Makin 1998
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Networks trained for object recognition encode part-like features in their deeper layers (Zeiler & Fergus 2014), whereby the presentation of new types of objects can activate novel combinations of feature detectors.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Zeiler & Fergus 2014
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Handwritten characters are inherently compositional, where the parts are pen strokes, and relations describe how these strokes connect to each other.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“the MNIST benchmark includes 6,000 examples of each handwritten digit”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites LeCun et al. 1998
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Yet, at least for image and caption generation, these tasks have been mostly studied in the big data setting that is at odds with the impressive human ability to generalize from small data sets”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“These abilities are not independent; rather they hang together and interact (Solomon et al. 1999), coming for free with the acquisition of the underlying concept”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Solomon et al. 1999
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In both cases, the algorithms are clearly using information less efficiently than a person learning to perform the same tasks”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“A scene from the game is a composition of various object types, including birds, fish, ice floes, igloos, and so on (Fig. 2).”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These programs allow the model to express causal knowledge about how the raw data are formed, and the probabilistic semantics allow the model to handle noise and perform creative tasks”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Representing this compositional structure explicitly is both more economical and better for generalization, as noted in previous work on object-oriented reinforcement learning (Diuk et al. 2008).”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Diuk et al. 2008
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The following sections discuss the three main ingredientscompositionality, causality, and learning-to-learnthat were important to the success of this framework and, we believe, are important to understanding human learning as rapid model building more broadly.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- The authors state this as an assumption: The success of the BPL framework in the Characters Challenge can be generalized to understanding human learning as rapid model building.
In the paper
“Lopez-Paz et al. (2015) introduced a discriminative, data-driven framework for distinguishing the direction of causality from examples.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Lopez-Paz et al. 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Concept learning and vision models that use causality are usually generative (as opposed to discriminative; see Glossary in Table 1), but not every generative model is also causal.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“For example, Liberman et al. (1967) argued that the richness of speech perception is best explained by inverting the production plan, at the level of vocal tract movements, to explain the large amounts of acoustic variability and the blending of cues across adjacent phonemes.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Liberman et al. 1967
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It also suggests an additional way to build on the successes of deep learning, where efficient inference and scalable learning are important strengths of the approach.”
§ Building machines that learn and think like people > 4.3. Thinking Fast
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Hierarhical Bayesian models operating over probabilistic programs (Goodman et al. 2008;Lake et al. 2015a;Tenenbaum et al. 2011) are equipped to deal with theory-like structures and rich causal representations of the world, yet there are formidable algorithmic challenges for efficient inference.”
§ Building machines that learn and think like people > 4.3. Thinking Fast
What the sources say
- Not checked yetcites Goodman et al. 2008
- Not checked yetcites Lake et al. 2015a
- Not checked yetcites Tenenbaum et al. 2011
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Whether the person is a child or a seasoned gamer, it seems obvious that interacting with the birds and fish will change the game state in some way, either good or bad, because video games typically yield costs or rewards for these types of interactions (e.g., dying or points).”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A causal model of Frostbite would have to be more complex, gluing together object representations and explaining their interactions with intuitive physics and intuitive psychology, much like the game engine that generates the game dynamics and, ultimately, the frames of pixel images.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Yet, if such a system aims to learn compositionally structured causal models of each gamebuilt on a foundation of intuitive physics and psychologyit could transfer knowledge more efficiently and thereby learn new games much more quickly.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In contrast, whereas representing intuitive theories and structured causal models is less natural in deep neural networks, recent progress has demonstrated the remarkable effectiveness of gradient-based learning in high-dimensional parameter spaces.”
§ Building machines that learn and think like people > 4.3. Thinking Fast
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Incorporating causality may greatly improve these deep learning models; they were trained without access to causal data about how characters are actually produced, and without any incentive to learn the true causal process.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In general, richer and more structured models require more complex and slower inference algorithms, similar to how complex models require more data, making the speed of perception and thought all the more remarkable.”
§ Building machines that learn and think like people > 4.3. Thinking Fast
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Computing a probability distribution over an entire space of programs is usually intractable, and often even finding a single high-probability program poses an intractable search problem.”
§ Building machines that learn and think like people > 4.3. Thinking Fast
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Most basically, they immediately parse the game environment into objects, types of objects, and causal relations between them.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“BPL could also benefit from deeper forms of learning-tolearn than it currently does.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
In the paper
“Graves ( 2014) learned a generative model of cursive handwriting using a recurrent neural network trained on handwriting data.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Graves 2014
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Capturing more human-like learning-to-learn dynamics in deep networks and other machine learning approaches could facilitate much stronger transfer to new tasks and new problems.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Some of the important structure it exploits to generalize well is built in to the prior and not learned from the background pre-training, whereas people might learn this knowledge, and ultimately, a human-like machine learning system should as well.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Most prominently, it has been proposed that humans can approximate Bayesian inference using Monte Carlo methods, which stochastically sample the space of possible hypotheses and evaluate these samples according to their consistency with the data and prior knowledge (Bonawitz et al. 2014;Gershman et al. 2012;Ullman et al. 2012b;Vul et al. 2014).”
§ Building machines that learn and think like people > 4.3. Thinking Fast
What the sources say
- Not checked yetcites Bonawitz et al. 2014
- Not checked yetcites Gershman et al. 2012
- Not checked yetcites Ullman et al. 2012b
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Deep neural networks could play a role in two ways: by serving as a bottom-up proposer to make probabilistic inference more tractable in a structured generative model (sect.4.3.1)or by serving as the causal generative model if imbued with the right set of ingredients.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“People also understand that video games like these have goals, which often involve approaching or avoiding objects based on their type.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If deep neural networks could adopt similarly compositional, hierarchical, and causal representations, we expect they could benefit more from learningto-learn.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
None of the sources cited for this claim have been checked yet.
In the paper
“In hierarchical Bayesian modeling (Gelman et al. 2004), a general prior on concepts is shared by multiple specific concepts, and the prior itself is learned over the course of learning the specific concepts (Salakhutdinov et al. 2012;2013).”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
What the sources say
- Not checked yetcites Gelman et al. 2004
- Not checked yetcites Salakhutdinov et al. 2012
- Not checked yetcites Salakhutdinov et al. 2013
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The strong priors, constraints, or inductive bias needed to learn a particular task quickly are often shared to some extent with other related tasks.”
§ Building machines that learn and think like people > 4.2. Learning as rapid model building
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“This process might occur offline (e.g., in dreaming or quiet wakefulness), suggesting a form of consolidation in reinforcement learning (Gershman et al. 2014).”
§ Building machines that learn and think like people > 4.3.2. Model-based and model-free reinforcement
What the sources say
- Not checked yetcites Gershman et al. 2014
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Some evidence for inferential correlations in humans was reported by Gershman and Goodman (2014).”
§ Building machines that learn and think like people > 4.3. Thinking Fast
What the sources say
- Not checked yetcites Gershman and Goodman 2014
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Another avenue for potential integration is through differentiable programming (Dalrymple 2016), by ensuring that the programlike hypotheses are differentiable and thus learnable via gradient descenta possibility discussed in the concluding section (Section 6.1).”
§ Building machines that learn and think like people > 4.3. Thinking Fast
What the sources say
- Not checked yetcites Dalrymple 2016
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Language also facilitates more powerful learning-to-learn and compositionality (Mikolov et al. 2016), allowing people to learn more quickly and flexibly by representing new concepts and thoughts in relation to existing concepts”
§ Building machines that learn and think like people > 5.3. Language is essential for human intelligence. Why is
What the sources say
- Not checked yetcites Mikolov et al. 2016
- Not checked yetcites Lupyan & Bergen 2016
- Not checked yetcites Lupyan & Clark 2015
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“understanding language and its role in intelligence goes hand-in-hand with understanding the building blocks discussed in this article.”
§ Building machines that learn and think like people > 5.3. Language is essential for human intelligence. Why is
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We conjecture that a competent Frostbite player can easily shift behavior appropriately, with little or no additional learning, and it is hard to imagine a way of doing that other than having a model-based planning approach in which the environment model can be modularly combined with arbitrary new reward functions and then deployed immediately for planning.”
§ Building machines that learn and think like people > 4.3.2. Model-based and model-free reinforcement
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Thus, a marriage of flexibility and efficiency might be achievable if we use the human reinforcement learning systems as guidance.”
§ Building machines that learn and think like people > 4.3.2. Model-based and model-free reinforcement
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
In the paper
“Behavior can persist for weeks or months, whereas LTP decays to baseline over the course of days”
§ Building machines that learn and think like people > 5.2. Biological plausibility suggests theories of intelligence should start with neural networks
What the sources say
- Not checked yetcites Power et al. 1997
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Deep learning models could incorporate these ingredients through some combination of additional structure and perhaps additional learning mechanisms, but for the most part have yet to do so.”
§ Building machines that learn and think like people > 5.1. Comparing the learning speeds of humans and neural networks on specific tasks is not meaningful, because humans have extensive prior experience
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“Schulz (2012b) has suggested that abstract structural properties of problems contain information about the abstract forms of their solutions.”
§ Building machines that learn and think like people > 4.3. Thinking Fast
What the sources say
- Not checked yetcites Schulz 2012b
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Learned behavior is rapidly re-acquired after extinction (Bouton 2004), whereas no such facilitation is observed for LTP (Jonge & Racine 1985).”
§ Building machines that learn and think like people > 5.2. Biological plausibility suggests theories of intelligence should start with neural networks
What the sources say
- Not checked yetcites Bouton 2004
- Not checked yetcites Jonge & Racine 1985
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“There may also be an intrinsic drive to reduce uncertainty and construct models of the environment (Edelman 2015;Schmidhuber 2015), closely related to learning-to-learn and multitask learning.”
§ Building machines that learn and think like people > 4.3.2. Model-based and model-free reinforcement
What the sources say
- Not checked yetcites Edelman 2015
- Not checked yetcites Schmidhuber 2015
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Any approach to human-like AI, whether based on deep learning or not, is likely to gain from incorporating these ingredients.”
§ Building machines that learn and think like people > 5.1. Comparing the learning speeds of humans and neural networks on specific tasks is not meaningful, because humans have extensive prior experience
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“These capacities are in place before children master language, and they provide the building blocks for linguistic meaning and language acquisition”
§ Building machines that learn and think like people > 5.3. Language is essential for human intelligence. Why is
What the sources say
- Not checked yetcites Carey 2009
- Not checked yetcites Jackendoff 2003
- Not checked yetcites Kemp 2007
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“autonomous cars could more accurately predict pedestrian behavior by inferring mental states, including their beliefs (e.g., Do they think it is safe to cross the street?Are they paying attention?)and desires”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“And like AlphaGo, they are also integrating model-free pattern recognition with model-based search.”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“causality helps infuse the recognition of existing tools or the learning of new ones with an understanding of their use, helping to connect different object models in the proper way”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“a human-like system would be able to learn both to recognize and to produce new instances from a small number of examples.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“looking at the brain can furnish important insights on how to face the architecture challenge”
§ Building machines that learn and think like people > Open Peer Commentary
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Robots and personal assistants such as cell phones cannot be pretrained on all possible concepts they may encounter.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“the human brain is more similar to a complex society of diverse neural networks, than to a large, single one”
§ Building machines that learn and think like people > Open Peer Commentary
What the sources say
- Not checked yetcites Minsky 1986
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“deep learning and other learning paradigms can move closer to human-like learning and thought if they incorporate psychological ingredients”
§ Building machines that learn and think like people > 6. Looking forward
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This type of psychological reasoning, along with other types of model-based causal and physical reasoning, are likely to be especially valuable in challenging and novel driving circumstances for which there are few relevant training data”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“a system may be able to quickly learn new concepts by constructing them from pre-existing primitive actions, informed by knowledge of the underlying causal process and learning-to-learn.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“They are using their core intuitive psychology and aspects of their intuitive physics (spatial and object representations).”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the fact that it cannot even conceive of these variants, let alone adapt to them autonomously, is a sign that it does not understand the game as humans do.”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“They are learning-tolearn with compositional knowledge.”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We see compositionality, causality, intuitive physics, and intuitive psychology as playing an increasingly important role in reaching true scene understanding.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The two hemispheres seem to follow two opposite criteria: an analogicalintuitive one, gradient descent-like, and a digital-rational one, vector quantization-like.”
§ Building machines that learn and think like people > Open Peer Commentary
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Perfect autonomous driving requires intuitive psychology.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In learning to play Go as quickly and as flexibly as they do, people are drawing on most of the cognitive ingredients this article has laid out.”
§ Building machines that learn and think like people > 6.1. Promising directions in deep learning
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“other drivers on the road have similarly complex mental states underlying their behavior”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Human intelligence is a prediction engine working on hypotheses, generated from a relatively small database and constantly verified through sequential sampling”
§ Building machines that learn and think like people > Open Peer Commentary
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we think that much of the intelligence of the brain resides in its architecture”
§ Building machines that learn and think like people > Open Peer Commentary
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If the scene includes people acting or interacting, it will be nearly impossible to understand their actions without thinking about their thoughts and especially their goals and intentions toward the other objects and agents they believe are present.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For an autonomous agent to effectively navigate and perform tasks in this environment, the agent would need intuitive physics to properly reason about stability and support.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A holistic model of the scene would require the composition of individual object models, glued together by relations.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In each case, the free combination of parts is not enough on its own: Although compositionality and learning-to-learn can provide the parts for new ideas, causality provides the glue that gives them coherence and purpose.”
§ Building machines that learn and think like people > 6.2. Future applications to practical AI problems
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“natural intelligence is still by far the best example of intelligence.”
§ Building machines that learn and think like people > 6. Looking forward
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Human-like learning and decision making surely do depend upon rich internal models”
§ Building machines that learn and think like people > Open Peer Commentary
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“it is not clear that detailed knowledge engineering will be realistically attainable in all areas we will want our agents to tackle”
§ Building machines that learn and think like people > Open Peer Commentary
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Machine performance may rival or exceed human performance on particular tasks, and algorithms may take inspiration from neuroscience or aspects of psychology, but it does not follow that the algorithm learns or thinks like a person.”
§ Building machines that learn and think like people > 6. Looking forward
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Future artificialintelligence systems will require sophisticated architectures, and knowledge of the brain might guide their construction”
§ Building machines that learn and think like people > Open Peer Commentary
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“the learning process must be informed and constrained by prior knowledge”
§ Building machines that learn and think like people > Open Peer Commentary
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“knowledge is grounded in exemplar-based learning and generalization, combined with high flexible generalization”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Natural intelligence appears to combine the largely reactive perception-action cycle of RL with a more active action-perception cycle, in which the cognitive system can act and deliberatively explore in order to test hypotheses.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In intuitive psychology, many inferences proceed without detailed causal generative models.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Lake et al.'s results are technically impressive, but may tell us little about object recognition in general.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The promise of DL networks (and at present it remains a promise) is that, with sufficiently broad training, they may support the development of systems that capture intuitive physics and intuitive psychology.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In physical reasoning, a model can be a set of constraints rather than a physics engine.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Over time, these updates may even result in distinct operating systems.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“Within this account the routine system may plausibly employ a DL-type network combined with (a hierarchical variant of) model-free reinforcement learning, whereas the non-routine system is more plausibly conceived of in terms of a model-based system (cf.Daw et al. 2005).”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
What the sources say
- Not checked yetcites Daw et al. 2005
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“First, simulation engines require both a precise predictive theory of the domain and a geometrically and physically precise description of the situation.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“More specifically, accounts of behaviour generation and regulation have long distinguished between automatic and deliberative behaviour.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“Thus, the contention scheduling/supervisory system theory of Norman and Shallice (1986) proposes that one systemthe contention scheduling systemcontrols routine, overlearned, or automatic behaviour, whereas a second systemthe supervisory systemmay bias or modulate the contention scheduling system in non-routine situations where deliberative control is exercised.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
What the sources say
- Not checked yetcites Norman and Shallice (1986)
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“What is missing from this discussion, however, is the recognition that children's developmental start-up software is shaped by their culture-specific social environment.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For example, the world knowledge used in vision presumably involves a combination of geometric, physical, and other knowledge, rather than just a causal theory of how the image was produced.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Neither result follows from the model.”
§ Building machines that learn and think like people > Leyla Roskan Çag lar and Stephen José Hanson
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We argue that (1) analogical comparison processes are central to human cognition; and (2) intuitive physical knowledge is captured by qualitative representations, rather than quantitative simulations.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“AGI has one existence proofour brains.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Qualitative representations provide symbolic, relational representations of continuous properties and an account of causality organized around processes of change.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Analogy provides a means of transferring prior knowledge.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
None of the sources cited for this claim have been checked yet.
In the paper
“Even visual tasks, such as character recognition, are more compactly represented by a network of relationships and objects than by an array of pixels, which is why human visual systems compute edges (Marr 1983;Palmer 1999).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Marr 1983
- Not checked yetcites Palmer 1999
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“We are not saying that an AI could not be created to have genuine interests, but that is down a very long road (Dennett 2017;Hurley et al. 2011).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Dennett 2017
- Not checked yetcites Hurley et al. 2011
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“long before that day arrives, if it ever does, we will have AIs that can communicate with natural language with their users (not collaborators).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Although some promising current work suggests that genuine human consciousness depends on a fundamental architecture that would require having interests (Deacon 2012;Dennett 2013), long before that day arrives, if it ever does, we will have AIs that can communicate with natural language with their users (not collaborators).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Deacon 2012
- Not checked yetcites Dennett 2013
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Because structure mapping allows the use of relational representations, the system also provided explanations, the lack of which is a significant drawback of distributed representations.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“spatial lateral connections between oriented features are a predominant feature of the visual cortex and are known to play a role in enforcing contour continuity.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This and many other experiments suggest that analogy not only can explain human transfer learning, but also can provide new techniques for machine learning.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Moreover, qualitative models can explain aspects of social reasoning, including blame assignment (Tomai & Forbus 2008) and moral decision making (Dehghani et al. 2008), suggesting that they are important in intuitive psychology as well.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Tomai & Forbus 2008
- Not checked yetcites Dehghani et al. 2008
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We also agree that human cognition relies heavily on structured relational representations.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Even the most powerful of existing AIs are intelligent tools, not colleagues, and whereas they can be epistemically authoritative (within limits we need to characterize carefully), and hence will come to be relied on more and more, they should not be granted moral authority or responsibility because they do not have skin in the game: they do not yet have interests, and simulated interests are not”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“we agree that rapid computation over structured representations is a major feature of human cognition.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We humans eventually bootstrap this behavioral competence into reflective comprehension, something more like a theory and something that is probably beyond language-less animals.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is hard to see how a Monte Carlo simulation approach would capture either the semantics of language about processes or the findings of the conceptual change literature.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Human emotion is probably the biggest difference between people and AI machines.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For example, not reaching an important goal can make a person angry.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Emotions modulate human behavior; the how of the behavior is determined by the emotions.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This protocol should be relatively fixed in a given species and lineage, and have the ability to be scaled up over development and evolution.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“the brain appears to largely show dynamic routing, sparse connectivity, and feedback among many hierarchical levels.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In this sense, human intelligence controls itself, reprogramming its own programs.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although MCMC has asymptotic guarantees”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Motivation can explain why a certain plan has priority and why it is executed, or why a certain action is stopped.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Cortical neurons, like Internet hosts, are separated by relatively short network distances, and have the potential for communication along many possible routes within milliseconds.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We should expect that brains adopt analogousif not homologoussolutions when conditions require.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Including such features in computational models may better approximate and explain biological function, which could in turn spawn better AI.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“it is suggested that an additional”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
In the paper
“the number of Internet hostseach of which can potentially communicate with any other within millisecondshas increased without major disruption over a few decades, to surpass the number of neurons in the cortex of many primates including the macaque (Fasolo 2011).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Fasolo 2011
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“in neural networks, one commonly employs a fixed routing system, all-to-all connectivity between layers, and feedback only between adjacent layers.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Emotions are shortcuts.Emotions are the framework in which cognition happens (e.g., Bach 2009;Dörner 2001).”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
What the sources say
- Not checked yetcites Bach 2009
- Not checked yetcites Dörner 2001
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The function of emotions is to adjust behavior to the demands of the current situation.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although a packet-switched routing protocol would not necessarily improve current deep learning systems, it may be better suited to modeling approaches that more closely approximate cortical networks' structure and function.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These features may make such systems well suited to learning a particular input space, but ill suited to flexible processing and efficient handling of new circumstances.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Despite lacking theoretical guarantees, MP has been known to work well in many practical cases”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Anger means high activation, quick and rough perception, little planning and deliberation, and making a quick choice.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Perhaps emotions can partly explain why humans learn”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In brief, a theory or a computational model of human intelligence that focuses solely on cognition is not a real theory of human intelligence.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the same approach could be used with meta-tasks that are extremely common as a result of sociocultural conventions, such as”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Fully addressing the challenges Lake et al. poserather than building in compositional knowledge structures that will ultimately prove limitingis a long-term challenge for the science of learning.”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These errors may be an inevitable part of the learning process by which models are updated based on experience.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Measuring the similarity of processing dynamics between a model and a brain has to rely on summary statistics of the activity and may be equally possible for neural and cognitive models.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These deficiencies are pervasive and have real-world consequences.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“For example, one could test whether the visual representation of characters in high-level visual regions reflects the similarity predicted by the generative model of character perception proposed by Lake et al. (2015a).”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
What the sources say
- Not checked yetcites Lake et al. 2015a
hedgedcorrelational- Asserted: fails — The authors may not put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The authors may not put it forward as true. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“many continue to believe that immunisation increases the risk of autism and their refusal to immunise has decreased the population's immunity to preventable diseases (Larson et al. 2011;Silverman & Hendrix 2015).”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
What the sources say
- Not checked yetcites Larson et al. 2011
- Not checked yetcites Silverman & Hendrix 2015
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, humans are biological organisms, and so”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Applying a causal model, especially one based on intuitive understanding, is essentially a gamble.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Humans learn complex skills in a domain after previously learning simpler ones, gradually building structured knowledge as they learn.”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As long as major components of human intelligence are out of the reach of machines, we are obviously far from understanding the human brain and cognition.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Avoiding a commitment to symbolic compositionality increases one's flexibility to respond to sometimes subtle influences of context and allows for the possibility of more robust learning across contexts.”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“One reason humans might be able to learn from fewer games than a neural network trained on playing chess as a single integrated task is that humans receive feedback on many of these tasks throughout learning, and this both allows more feedback from a single experience”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one. The quote only partly states this claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“A model must not only reach human levels of task performance, but also predict detailed patterns of behavioral responses (e.g., errors and reaction times on particular instances of a task).”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This reflects the fact that current models learn from scratch.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although the meta-tasks used in these first attempts only roughly reflect the training environment that humans face (we probably do not face explicit one-shot classification problems that frequently)”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“A good model should somehow match the brain's dynamics of information processing.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we believe that human knowledge acquisition and generalization can be understood without building in a commitment to domain-specific knowledge structures or compositional knowledge representation.”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Knowledge of physical relations between objects and psychological relations between agents brings huge advantages.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It provides a wealth of transferable information that allows humans to quickly apprehend a new situation.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Their inferences require realistically small amounts of data, but unrealistically large amounts of computation, and, as a result, their highlevel feats of cognition do not always scale to complex real-world challenges.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The brain's inference process appears to involve recurrent cycles of message passing at multiple scales, from local interactions within an area to long-range interactions between higher-and lower-level representations.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our models are often incorrect, resistant to correction, and applied inappropriately to new situations.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This enables us to infer past causes and future implications, with a focus on what matters to our behavioral success.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This interaction of motivation, cognition, and emotion, is the real strength of human intelligence compared with artificial intelligence.”
§ Building machines that learn and think like people > Thinking like animals or thinking like colleagues?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This is clearly not the same as human learning, which builds cumulatively on prior learning.”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Failures to revise false causal models are far from rare.In fact, they seem to be an inherent part of human reasoning.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
What the sources say
- Not checked yetcites Lewandowsky et al. 2012
- Not checked yetcites Taylor & Ahn 2012
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“They can rapidly recognize objects as humans can, and their internal representations are remarkably similar to those of the human ventral stream (Eickenberg et al. 2016;Güçlü & van Gerven 2015;Khaligh-Razavi & Kriegeskorte 2014;Yamins et al. 2014).”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
What the sources say
- Not checked yetcites Eickenberg et al. 2016
- Not checked yetcites Güçlü & van Gerven 2015
- Not checked yetcites Khaligh-Razavi & Kriegeskorte 2014
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In games like Chess or Go, human learners can receive feedback not only on the outcome of an entire gamedid the learner succeed or fail?but also on individual steps in an action sequence.”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“our causal knowledge is almost always incomplete and sometimes completely wrong (Rozenblit & Keil 2002).”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
What the sources say
- Not checked yetcites Rozenblit & Keil 2002
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“This sort of richer feedback can easily be incorporated into neural networks, and doing so can enhance learning (Gülçehre and Bengio 2016).”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
What the sources say
- Not checked yetcites Gülçehre and Bengio 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, even two biological brains of the same species will have different numbers of neurons, and any given neuron may be idiosyncratically specialized, and may not have an exact match in the other brain.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
hedgedn = 2- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In cognitive science, the empirical support for models comes from behavioral data.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Appeals to evolution, although they may be plausible for some tasks, seem out of place in domains of recent human invention such as character-based writing systems.”
§ Building machines that learn and think like people > Building on prior knowledge without building it in
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“combining the computational power of deep-neural networks with model-building capacities could indeed bring solutions to some of the world's most pressing problems.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We bring complex knowledge and dynamic models of the world to bear on the sensory data.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“We agree with the authors' assertion that “reverse engineering human intelligence can usefully inform artificial intelligence and machine learning” (sect.1.1, para.3)”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
What the sources say
- Not checked yetcites sect.1.1, para.3
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Cost-benefit-based inferences about situations such as the one depicted in the leftmost picture in Figure 6 of Lake et al. will likely conclude that one agent has a desire to kill the other, and that he or she values higher the state of the other being dead than alive.”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“It has been argued that the process of human decision making does not typically involve rational utility maximization (e.g., Hertwig & Herzog 2009).”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
What the sources say
- Not checked yetcites Hertwig & Herzog 2009
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We argue that human-like machines should be designed to make decisions in transparent and comprehensible ways, which can be achieved by accurately mirroring human cognitive processes.”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
- Rests on an assumption: AI algorithms draw inspiration from human cognitive systems where humans perform better than machines.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although as-if models relying on cost-benefit analysis might be reasonably transparent and comprehensible, for example, when problems are simple and do not involve moral considerations, this might not always be the case.”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the discussed example, although both a sheriff and a contract killer would have the same goal to end another person's life, the difference in their identity would change the human interpretation in a significant way.”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“the authors' proposal of an “intuitive psychology” is grounded in the naïve utility calculus framework (Jara-Ettinger et al. 2016)”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
What the sources say
- Not checked yetcites Jara-Ettinger et al. 2016
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
In the paper
“Ontological confusions have been linked to people's acceptance of alternative medicine, potentially leading an individual to choose an ineffective treatment over evidence-based treatments, sometimes at extreme personal risk (Lindeman 2011).”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
What the sources say
- Not checked yetcites Lindeman 2011
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We welcome the applicability of naïve utility calculus for inferring simple information concerning agent-specific variables, such as goals and competence level.”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Developers of AI systems should proceed with caution, as these properties of human causal modelling produce pervasive biases, and may be symptomatic of the use of mental models rather than the limitations on human cognition.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
In the paper
“Heuristics not only are meant to capture ecologically rational human decision mechanisms (see Todd & Gigerenzer 2007)”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
What the sources say
- Not checked yetcites Todd & Gigerenzer 2007
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Lake et al. acknowledge this problem and call for structured cognitive representations, which are required for classifying social situations.”
§ Building machines that learn and think like people > Pierre-Yves Oudeyer
What the sources say
- Not checked yetcites Lake et al.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
None of the sources cited for this claim have been checked yet.
In the paper
“For example, effective model-based decision-making is associated with capacities for learning and transferring abstract rules (Don et al. 2016), and for cognitive control (Otto et al. 2015), which may potentially be far more powerful in future AI systems.”
§ Building machines that learn and think like people > Nikolaus Kriegeskorte and Robert M. Mok
What the sources say
- Not checked yetcites Don et al. 2016
- Not checked yetcites Otto et al. 2015
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper relies on this without support.
People are better than machines at solving a range of difficult computational problems including concept learning, scene understanding, language acquisition, language understanding, and speech recognition.
“Despite recent computational achievements, people are better than machines at solving a range of difficult computational problems, including concept learning, scene understanding, language acquisition, language understanding, speech recognition, and so on.”
The paper relies on this without support.
Children possess the ability and desire to uncover underlying causes of sparsely observed events and use that knowledge to go beyond limited data.
“Children come with the ability and the desire to uncover the underlying causes of sparsely observed events and to use that knowledge to go far beyond the paucity of the data.”
The paper relies on this without support.
People can comprehend a novel scene in a fraction of a second, or a novel utterance in little more than the time it takes to say and hear it.
“People can comprehend a novel scene in a fraction of a second, or a novel utterance in little more than the time it takes to say it and hear it.”
The paper relies on this without support.
Once a causal model of a task is learned, humans can use the model to plan action sequences that maximize future reward.
“Once a causal model of a task has been learned, humans can use the model to plan action sequences that maximize future reward.”
The paper relies on this without support.
Humans combine model-based and model-free learning algorithms both competitively and cooperatively, and these interactions are supervised by metacognitive processes.
“We review evidence that humans combine model-based and model-free learning algorithms both competitively and cooperatively and that these interactions are supervised by metacognitive processes.”
The paper relies on this without support.
People can integrate across multiple examples of a character to infer optional elements, such as the cross-bar in '7's, and combine variants into a single coherent representation.
“Furthermore, people can efficiently integrate across multiple examples of a character to infer which have optional elements, such as the horizontal cross-bar in '7's, combining different variants of the same character into a single coherent representation.”
The paper relies on this without support.
The core ingredients of human intelligence are not present in most current learning-based AI systems, and not all of them are present together.
“they are key building blocks, which are not present in most current learningbased AI systemscertainly not all present together”
The paper relies on this without support.
The DQN starts completely from scratch, without prior experience.
“The DQN is starting completely from scratch”
The authors state this as an assumption.
The success of the BPL framework in the Characters Challenge can be generalized to understanding human learning as rapid model building.
“The following sections discuss the three main ingredientscompositionality, causality, and learning-to-learnthat were important to the success of this framework and, we believe, are important to understanding human learning as rapid model building more broadly.”
The paper relies on this without support.
The Characters Challenge and the Frostbite Challenge are representative testbeds for studying human-like learning and thinking.
“We can see this potential in both of our challenge problems.”
The authors state this as an assumption.
Cognitive plausibility offers a surer foundation than biological plausibility for theories of intelligence.
“For now, we believe cognitive plausibility offers a surer foundation.”
The paper relies on this without support.
Brain cells are not motile enough to selectively deliver messages to their destinations.
“Given that brain cells themselves are not motile enough to selectively deliver messages to their destination (unlike cells in the immune system, for example)”
The paper relies on this without support.
The brain implements a generative model.
“what kind of generative model the brain implements”
The paper relies on this without support.
The power of neural networks lies in their ability to encode rich featural and contextual information.
“On the other hand, the power of neural networks lies precisely in their ability to encode rich featural and contextual information.”
The paper relies on this without support.
Experience with particular causal relations likely correlates with experience of more superficial features.
“Given that experience with particular causal relations is likely to correlate with experience of more superficial features, a more powerful AI model generator may still suffer similar problems when faced with the difficult decision of which model to apply to a new situation.”
The paper relies on this without support.
Current deep learning research does not include physical embodiment.
“and yet it is out of the picture in current deep learning research”
The paper relies on this without support.
Deep learning architectures often concentrate on inference and optimization.
“Deep learning architectures often focus on inference and optimization.”
The paper relies on this without support.
Learning happens through complex dynamical interactions among inference, memory, attention, motivation, low-level sensorimotor loops, embodiment, and social interaction.
“learning occurs through complex dynamical interaction among systems of inference, memory, attention, motivation, low-level sensorimotor loops, embodiment, and social interaction”
The paper relies on this without support.
Attention and memory are among the ingredients already present in current deep learning research.
“Although some of these ingredients are part of current DL research, (e.g., attention and memory)”
The paper relies on this without support.
AI algorithms draw inspiration from human cognitive systems where humans perform better than machines.
“Artificial intelligence algorithms seek inspiration from human cognitive systems in areas where humans outperform machines.”
The paper relies on this without support.
A human-like classification of the Figure 6 scene would conclude that it shows either a legal execution or a murder.
“a human-like classification of such a scene would rather reach the conclusion that the scene depicts either a legal execution or a murder”
The paper relies on this without support.
People interacting with the system will probably want a justification for why it chose one interpretation over another.
“Humans interacting with the system will likely expect a justification of why it has picked one interpretation rather than another”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Specifically, we know that models trained with self-supervision can capture the underlying structures and relationships behind their training data [51] -exactly what we need from a compression heuristic.”
From Learning to (Learn at Test Time): RNNs with Expressive Hidden States (2024) · cites this paper as [51]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Bayesian inference and evidence accumulation, which are cornerstone computations for AI ( 2 ), are basic unconscious mechanisms for humans.”
From What is consciousness, and could machines have it? (2017) · cites this paper as [2]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Bayesian approaches to AI ( 2 , 73 ) have recognized the usefulness of learning generative models that can be jointly used for actual perception (present), prospective planning (future), and retrospective analysis (past).”
From What is consciousness, and could machines have it? (2017) · cites this paper as [2]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“without possessing any true empathy or social understanding”
From The benefits and dangers of anthropomorphic conversational agents (2025) · cites this paper as [63]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“it remains obviously true that LLMs' inner workings are fundamentally different to human cognition (63), and that they are incapable of feeling or even understanding emotion or language in any genuine sense (27, 64).”
From The benefits and dangers of anthropomorphic conversational agents (2025) · cites this paper as [63]
Experimental — accuracy not yet measured
The cited source says what the claim attributes to it.
In the citing paper
“there is increasing evidence from cognitive science that human reasoning is scaffolded by rich causal models of the world (Pearl, 1988;Lake et al., 2017), and that humans can intervene on these models to perform rapid and flexible counterfactual simulations (Lagnado et al., 2013;Gerstenberg et al., 2017Gerstenberg et al., , 2021)).”
From Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks (2024) · cites this paper as Lake et al., 2017
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“In this paper, we begin with the observation that self-supervised learning can compress a massive training set into the weights of a model such as an LLM, which often exhibits deep understanding about the semantic connections among its training data -exactly what we need from a compression heuristic.”
From Learning to (Learn at Test Time): RNNs with Expressive Hidden States (2024) · cites this paper as [51]
Experimental — accuracy not yet measuredIn the citing paper
“It is commonly held that although neural networks can achieve a high level of performance within a narrowly-defined task domain, they cannot robustly generalize what they learn to new problems in the way that human learners do.”
From Emergent analogical reasoning in large language models (2023) · cites this paper as [48]
In the citing paper
“Cognitive scientists have long hypothesized that variable binding plays a central role in analogical reasoning, and abstract reasoning more broadly, as it potentially allows generalization of abstract roles across different contexts.”
From Emergent analogical reasoning in large language models (2023) · cites this paper as [48]
In the citing paper
“Initially applied to basic sensory and motor processes23,24, Bayesian models have begun to engage complex cognition, including the way our minds model the physical and social world2.”
From Cognitive computational neuroscience (2018) · cites this paper as [2]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Research works printed but not linked: 40
- 1961, GPS, A program that simulates human thought
- 1966, Cognitive psychology
- 2012, JMLR Workshop on Unsupervised and Transfer Learning, 27, 195
- 2007, Contemporary Educational Psychology, 25, 54
- 1996, Rethinking innateness
- 2003, Artificial intelligence: A modern approach
- 2015, Journal of Experimental & Theoretical Artificial Intelligence, 28, 751
- 2014, Proceedings of Machine Learning Research, 32, 647
- 1986, Machine Learning, 1, 47
- 1986, Parallel distributed processing: Explorations in the microstructure of cognition, Vol. 1
- 1986, Parallel distributed processing: Explorations in the microstructure of cognition, Vol. 1, 216
- 2004, Semantic cognition
- 2015, Communications of the ACM, 58, 92
- 1986, Parallel distributed processing: Explorations in the microstructure of cognition, Vol. 2
- 1995, An invitation to cognitive science: vol. 2. Visual cognition, 297
- Ghahramani, 2014, Advances in neural information processing systems 27 (NIPS 2014)
- 1979, Cognitive Science, 3, 275
- 1950, Mind, 59, 433
- 2007, Nature, 450, 57
- 2010, Origins of human communication
- 1962, IRE Transactions on Information Theory, 8, 155
- 1982, Vision
- 2003, Journal of Experimental Psychology: Learning, Memory, and Cognition, 29, 1141
- 2007, The stuff of thought: Language as a window into human nature
- 1989, Categorization and naming in children
- 1978, Papers and Reports on Child Language Development, 15, 17
- 1998, Cognitive Psychology, 282, 243
- Bresnan, 1978, Linguistic theory and psychological reality, 264
- Woodward, 2009, Learning and the infant mind, 66
- 2006, Mind as machine: A history of cognitive science
- 2014, Machine: earning: An artificial intelligence approach, vol. 3
- 2014, PLoS Computational Biology, 10
- 1990, Technometric, 33, 251
- 1975, The psychology of computer vision, 157
- Damon, 1998, Handbook of child psychology: Vol. 2. Cognition, perception, and language development, 523
- 1992, Machine Learning, 8, 279
- 2012, IEEE Signal Processing Magazine, 29, 82
- 2013, Frontiers in Psychology, 4, 365
- 2015, Science, 34, 273
- 2004, Bayesian data analysis
Cited by
Sorted by citations
Items 1,001–1,013 of 1,013
Universal linguistic inductive biases via meta-learning
McCoy, R. T., Grant, E., Smolensky, P., Griffiths, T. L., & Linzen, T. (2020) · arXiv · doi:10.48550/arxiv.2006.16324 · Cited by 13
Rudroff, T., Rainio, O., & Klén, R. (2024) · Brain Sciences · doi:10.3390/brainsci14111111 · Cited by 11
Generating Meaning: Active Inference and the Scope and Limits of Passive AI
Pezzulo, G., Parr, T., Cisek, P., Clark, A., & Friston, K. (2023) · doi:10.31234/osf.io/8xgzv · Cited by 8
Procedural Generalization by Planning with Self-Supervised World Models
Anand, A., Walker, J., Li, Y., Vértes, E., Schrittwieser, J., Ozair, S., Weber, T., & Hamrick, J. B. (2021) · arXiv · doi:10.48550/arxiv.2111.01587 · Cited by 5
When Can AI Models Explain Learning? Validity Criteria for AI as Cognitive Models in Education
Wang, P., Viberg, O., Law, E. L.-C., & Greiff, S. (2026) · Educational Psychology Review · doi:10.1007/s10648-026-10202-y · Cited by 3
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
Matthews, M., Beukman, M., Lu, C., & Foerster, J. (2024) · arXiv · doi:10.48550/arxiv.2410.23208 · Cited by 1
General agents contain world models
Richens, J., Abel, D., Bellot, A., & Everitt, T. (2025) · arXiv · doi:10.48550/arxiv.2506.01622 · Cited by 30
Understanding Agent Complexity Through Affordances
Baker, B., & Roberts, S. (2025) · Minds and Machines · doi:10.1007/s11023-025-09748-7
2022 roadmap on neuromorphic computing and engineering
Christensen, D. V., Dittmann, R., Linares-Barranco, B., Sebastian, A., Le Gallo, M., Redaelli, A., Slesazeck, S., Mikolajick, T., Spiga, S., Menzel, S., et al. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac4a83
End-to-End Test-Time Training for Long Context
Tandon, A., Dalal, K., Li, X., Koceja, D., Rød, M., Buchanan, S., Wang, X., Leskovec, J., Koyejo, S., Hashimoto, T., et al. (2025) · arXiv
Forgetting to Learn Logic Programs
Cropper, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5776
The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning
Vahdati, S., Aioanei, A., Suresh, H., & Lehmann, J. (2026) · arXiv · doi:10.48550/arxiv.2603.13372
Metadata
- Authors
- Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J.
- Affiliations
- New York University (US)
- Massachusetts Institute of Technology (US)
- Harvard University (US)
- Venue
- Behavioral and Brain Sciences
- Publisher
- Cambridge University Press (CUP)
- Published
- 2016-11-24
- Volume
- 40
- Pages
- e253-e253
- ISSN
- 0140-525X (ISSN-L)
- 1469-1825
- OpenAlex
- W2328078142
- Cited by
- 2,550
- References
- 228
- Citations by year
- 2026: 244 · 2025: 273 · 2024: 305 · 2023: 274 · 2022: 253 · 2021: 358 · 2020: 282 · 2019: 280 · 2018: 168 · 2017: 90 · 2016: 19
- FWCI
- 152.60
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Behavioral and Brain Sciences (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Funders
- National Science Foundation (ES/K002201/1, RP2012-V-022, 1231216)
- York University
- Leverhulme Trust (RP2012-V022, ES/K002201/1)
- Research Councils UK (EP/K039830/1)
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (146702, 144413)
- Companhia Brasileira de Metalurgia e Mineração (CCF-1231216)
- Economic and Social Research Council (ES/K002201/1, RP2012-V-022, K002201, ES/K002201/)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Cognitive Computing and Networks
- Keywords
- human-like learning, artificial intelligence, causal models, explanation and understanding, intuitive theories, compositionality, meta-learning, knowledge generalization, cognitive models, deep neural network
- MeSH terms
- Achievement, Artificial Intelligence, Humans, Intelligence, Thinking, Visual Perception, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
