A Roadmap Towards Machine Intelligence
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
The development of intelligent machines is one of the biggest unsolved challenges in computer science. In this paper, we propose some fundamental properties these machines should have, focusing in particular on communication and learning. We discuss a simple environment that could be used to incrementally teach a machine the basics of natural-language-based communication, as a prerequisite to more complex interaction with human users. We also present some conjectures on the sort of algorithms the machine should support in order to profitably learn from the environment.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
I.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290 · cited 1×
“We owe, of course, a large debt to the seminal work of Turing (1950).”
BackgroundReinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 2×
“This roadmap constitutes only the beginning of a long journey towards AI, and we hope other researchers will be joining it in pursuing the goals it outlined.”
BackgroundLearning and development in neural networks: the importance of starting small
Elman, J. L. (1993) · Cognition · doi:10.1016/0010-0277(93)90058-4 · Cited by 1,988 · cited 2×
“This is motivated by the observation that humans learn incrementally when developing complex skills, an idea that has also previously been studied in the context of recurrent neural network training by Elman (1993).”
BackgroundA formal theory of inductive inference. Part II
Solomonoff, R. J. (1964) · Information and Control · doi:10.1016/s0019-9958(64)90131-7 · Cited by 1,758
A formal theory of inductive inference. Part I
Solomonoff, R. J. (1964) · Information and Control · doi:10.1016/s0019-9958(64)90223-2 · Cited by 1,192 · cited 1×
“The idea of incremental learning, motivated by the same considerations as in the papers we just mentioned, also appears in Solomonoff (2002), a work which has much earlier roots in research on program induction (Solomonoff, 1964, 1997; Schmidhuber, 2004).”
ResultGraves, A., Wayne, G., & Danihelka, I. (2014) · arXiv · doi:10.48550/arxiv.1410.5401 · Cited by 1,058 · cited 1×
“One could think of solving sequence-manipulation problems such as those constituting the basis of our learning routine with relatively small extensions of established machine learning techniques (Graves et al., 2014; Grefenstette et al., 2015; Joulin and Mikolov, 2015).”
BackgroundTowards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
Weston, J., Bordes, A., Chopra, S., Rush, A. M., van Merriënboer, B., Joulin, A., & Mikolov, T. (2015) · arXiv · doi:10.48550/arxiv.1502.05698 · Cited by 670 · cited 1×
“In a similar spirit, Weston et al. (2015) present a set of question answering tasks based on synthetically generated stories.”
BackgroundSelf-citationSymbol Interdependency in Symbolic and Embodied Cognition
Louwerse, M. M. (2011) · Topics in Cognitive Science · doi:10.1111/j.1756-8765.2010.01106.x · Cited by 399 · cited 2×
“ch of the latter can be conveyed through linguistic means. For example, we can use language to talk about what we perceive with our senses, or to give instructions on how to operate in the world (see Louwerse, 2011, among others, for evidence that language encodes many perceptual aspects of our knowledge). Analogously…”
BackgroundCHILD: A First Step Towards Continual Learning
Ring, M. B. (1997) · Machine Learning · doi:10.1023/a:1007331723572 · Cited by 143
Cited by
40 years of cognitive architectures: core cognitive abilities and practical applications
Kotseruba, I., & Tsotsos, J. K. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-018-9646-y · Cited by 539
ParlAI: A Dialog Research Software Platform
Miller, A., Feng, W., Batra, D., Bordes, A., Fisch, A., Lu, J., Parikh, D., & Weston, J. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/d17-2014 · Cited by 315
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
Havrylov, S., & Titov, I. (2017) · arXiv · doi:10.48550/arxiv.1705.11192 · Cited by 195
Word meaning in minds and machines.
Lake, B. M., & Murphy, G. L. (2023) · Psychological Review · doi:10.1037/rev0000297 · Cited by 131
Metadata
- Authors
- Mikolov, T., Joulin, A., & Baroni, M.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2018
- Pages
- 29-61
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2181199551
- Cited by
- 80
- References
- 12
- FWCI
- 4.79
- Type
- conference paper
- Language
- en
- Open access
- green
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.