Theory learning as stochastic search in the language of thought
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
We present an algorithmic model for the development of children's intuitive theories within a hierarchical Bayesian framework, where theories are described as sets of logical laws generated by a probabilistic context-free grammar. We contrast our approach with connectionist and other emergentist approaches to modeling cognitive development. While their subsymbolic representations provide a smooth error surface that supports efficient gradient-based learning, our symbolic representations are better suited to capturing children's intuitive theories but give rise to a harder learning problem, which can only be solved by exploratory search. Our algorithm attempts to discover the theory that best explains a set of observed data by performing stochastic search at two levels of abstraction: an outer loop in the space of theories and an inner loop in the space of explanations or models generated by each theory given a particular dataset. We show that this stochastic search is capable of learning appropriate theories in several everyday domains and discuss its dynamics in the context of empirical studies of children's learning.
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
Causation, Prediction, and Search
Spirtes, P., Glymour, C., & Scheines, R. (2001) · doi:10.7551/mitpress/1754.001.0001 · Cited by 4,521
Connectionism and cognitive architecture: A critical analysis
Fodor, J. A., & Pylyshyn, Z. W. (1988) · Cognition · doi:10.1016/0010-0277(88)90031-5 · Cited by 4,022
Carey, S. (2009) · doi:10.1093/acprof:oso/9780195367638.001.0001 · Cited by 2,322
How to grow a mind: Statistics, structure, and abstraction
Tenenbaum, J. B., Kemp, C., Griffiths, T. L., & Goodman, N. D. (2011) · Science · doi:10.1126/science.1192788 · Cited by 1,815
Self-citationGopnik, A., & Meltzoff, A. N. (1997) · doi:10.7551/mitpress/7289.001.0001 · Cited by 1,479
Theory-based Bayesian models of inductive learning and reasoning
Tenenbaum, J. B., Griffiths, T. L., & Kemp, C. (2006) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2006.05.009 · Cited by 880
Self-citationAdvertisement for a Semantics for Psychology
Block, N., & Philosophy Documentation Center (1986) · Midwest Studies in Philosophy · doi:10.1111/j.1475-4975.1987.tb00558.x · Cited by 775
Statistically optimal perception and learning: from behavior to neural representations
Fiser, J., Berkes, P., Orbán, G., & Lengyel, M. (2010) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2010.01.003 · Cited by 672 · cited 1×
“We have not discussed at all the level of neural implementation, but recent proposals by a number of authors argue that analogous stochastic-sampling ideas could plausibly be used to carry out Bayesian learning in the brain (Fiser et al., 2010).”
Church: a language for generative models
Goodman, N., Mansinghka, V., Roy, D. M., Bonawitz, K., & Tenenbaum, J. B. (2012) · arXiv · doi:10.48550/arxiv.1206.3255 · Cited by 577
Self-citationProbabilistic models of cognition: exploring representations and inductive biases
Griffiths, T. L., Chater, N., Kemp, C., Perfors, A., & Tenenbaum, J. B. (2010) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2010.05.004 · Cited by 568
Self-citationA rational analysis of rule-based concept learning
Goodman, N. D., Tenenbaum, J. B., Feldman, J., & Griffiths, T. L. (2008) · Cognitive Science · doi:10.1080/03640210701802071 · Cited by 469
Harman, G. (1982) · Notre Dame Journal of Formal Logic · doi:10.1305/ndjfl/1093883628 · Cited by 355
Structured statistical models of inductive reasoning
Kemp, C., & Tenenbaum, J. B. (2009) · Psychological Review · doi:10.1037/a0014282 · Cited by 259
Self-citationBayesian sampling in visual perception
Moreno-Bote, R., Knill, D. C., & Pouget, A. (2011) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1101430108 · Cited by 182
Perceptual multistability predicted by search model for bayesian decisions.
Sundareswara, R., & Schrater, P. R. (2008) · Journal of Vision · doi:10.1167/8.5.12 · Cited by 112
Cited by
Building machines that learn and think like people
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017) · Behavioral and Brain Sciences · doi:10.1017/s0140525x16001837 · Cited by 2,550
Self-citationBuilding Machines That Learn and Think Like People
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2016) · arXiv · doi:10.48550/arxiv.1604.00289 · Cited by 2,550
Self-citationMind games: Game engines as an architecture for intuitive physics
Ullman, T. D., Spelke, E., Battaglia, P., & Tenenbaum, J. B. (2017) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2017.05.012 · Cited by 234
“Even in inference tasks where physics engines can be useful for evaluating candidate hypotheses or explanations, there remains the di ffi cult and separate problem of coming up with the right hypotheses in the first place [84, 32, 85].”
BackgroundSelf-citationQuilty-Dunn, J., Porot, N., & Mandelbaum, E. (2023) · Behavioral and Brain Sciences · doi:10.1017/s0140525x22002849 · Cited by 205
Formalizing Neurath’s ship: approximate algorithms for online causal learning.
Bramley, N. R., Dayan, P., Griffiths, T. L., & Lagnado, D. A. (2017) · Psychological Review · doi:10.1037/rev0000061 · Cited by 136
“…Lucas, Williams, & Kalish, 2009); hierarchical organization (Griffiths & Tenenbaum, 2009; Williamson & Gabbay, 2005); and temporal (Pacer & Griffiths, 2012) and spatial (Battaglia, Hamrick, & Tenenbaum, 2013; Ullman et al., 2012; Ullman, Stuhlmüller, Goodman, & Tenenbaum, 2014) semantics.”
Metadata
- Authors
- Ullman, T. D., Goodman, N. D., & Tenenbaum, J. B.
- Venue
- Cognitive Development
- Publisher
- Elsevier BV
- Published
- 2012-10
- Volume
- 27
- Issue
- 4
- Pages
- 455-480
- ISSN
- 0885-2014 (ISSN-L)
- OpenAlex
- W2150342508
- Cited by
- 91
- References
- 15
- FWCI
- 10.09
- Type
- journal article
- 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.