Josh Tenenbaum
Professor
Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology
Email: jbt AT mit DOT edu
Phone: 617-452-2010 (office), 617-253-8335 (fax)
Mail: Building 46-4015, 77 Massachusetts Avenue, Cambridge, MA 02139
Curriculum Vitae (as of October 2017)
If you are an undergraduate at MIT interested in research with our group, please send a short email about your interests and background (as specific as possible), with resume/CV and any previous research papers, to cocosci-urop@mit.edu. Thanks!
If you are applying to work with our group via an MIT PhD program, please consider applying to both the Department of Brain and Cognitive Sciences, and Electrical Engineering and Computer Science. I work with students through both programs. Students interested in computational cognitive modeling or cognitive AI are especially encouraged to apply to both, as they have different features and that will maximize your chances of acceptance. (Because I am not a primary EECS faculty member, you won't see my name on the list of prospective EECS PhD advisors but just mention me in your research statement and I will see your application.) I strongly encourage applications from students in groups underrepresented in cognitive science (especially computational cognitive science) or AI.
For all students, I am happy to recieve an email about your interests, but due to the volume of inquiries I receive, I cannot respond to most questions about PhD applications. Please don't take a lack of response as any lack of interest in your application! If you mention my name in your research statement, I will see your application, and I will make sure to keep an eye out for applications from any student who does email me.
My colleagues and I in the Computational Cognitive Science group want to understand that most elusive aspect of human intelligence: our ability to learn so much about the world, so rapidly and flexibly. I like to ask, "How do we humans get so much from so little?" and by that I mean how do we acquire our commonsense understanding of the world given what is clearly by today's engineering standards so little data, so little time, and so little energy.
Consider how given just a few relevant experiences, even young children can infer the meaning of a new word, the hidden properties of an object or substance, or the existence of a new causal relation or social rule. These inferences go far beyond the data given: after seeing three or four examples of "horses", a two-year-old will confidently judge whether any new entity is a horse or not, and she will be mostly correct, except for the occasional donkey or camel.
We want to understand these everyday inductive leaps in computational terms. What is the underlying logic that supports reliable generalization from so little data? What are its cognitive and neural mechanisms, and how can we build more powerful learning machines based on the same principles?
These questions demand a multidisciplinary approach. Our group's research combines computational models (drawing chiefly on Bayesian statistics, probabilistic generative models, and probabilistic programming) with behavioral experiments in adults and children. Our models make strong quantitative predictions about behavior, but more importantly, they attempt to explain why cognition works, by viewing it as an approximation to ideal statistical inference given the structure of natural tasks and environments.
While our core interests are in human learning and reasoning, we also work actively in machine learning and artificial intelligence. These two programs are inseparable: bringing machine-learning algorithms closer to the capacities of human learning should lead to more powerful AI systems as well as more powerful theoretical paradigms for understanding human cognition.
Current research in our group explores the computational basis of many aspects of human cognition: learning concepts, judging similarity, inferring causal connections, forming perceptual representations, learning word meanings and syntactic principles in natural language, noticing coincidences and predicting the future, inferring the mental states of other people, and constructing intuitive theories of core domains, such as intuitive physics, psychology, biology, or social structure.
The Computational Cognitive Science Group
Publications sorted by citation popularity
Publications sorted by recency
Computational rationality: A converging paradigm for intelligence in brains, minds and machines..Gershman, S. J., Horvitz, E. J., and Tenenbaum, J. B. (2015). Science 349(6245), 273-278. doi: 10.1126/science.aac6076
Simulation as an engine of physical scene understanding. Battaglia, P. W., Hamrick, J. B., and Tenenbaum, J. B. (2013). Proceedings of the National Academy of Sciences 110(45), 18327-18332. doi: 10.1073/pnas.1306572110
How to Grow a Mind: Statistics, Structure, and Abstraction. Tenenbaum, J. B., Kemp, C., Griffiths, T. L., and Goodman, N. D. (2011). Science 331 (6022), 1279-1285. Supporting Online Material.
The discovery of structural form. Kemp, C. and Tenenbaum, J. B. (2008). Proceedings of the National Academy of Sciences. 105(31), 10687-10692. Supporting information. Commentary by K. J. Holyoak. Code and data sets.
Bayesian models of cognition. Griffiths, T. L., Kemp, C., and Tenenbaum, J. B. (2008). In Ron Sun (ed.), Cambridge Handbook of Computational Cognitive Modeling. Cambridge University Press.
Pure reasoning in 12-month-old infants as probabilistic inference. Teglas, E., Vul, E., Girotto, V., Gonzalez, M., Tenenbaum, J. B., and Bonatti, L. L. (2011). Science 332, 1054-1059. Supporting Online Material.
Special issue of Trends in Cognitive Science, July 2006 (Vol. 10, Issue 7), on "Probabilistic Models of Cognition".
Optimal predictions in everyday cognition. Griffiths, T. L. and Tenenbaum, J. B. (2006). Psychological Science 17(9), 767-773. Article in The Economist.
A global geometric framework for nonlinear dimensionality reduction. J. B. Tenenbaum, V. De Silva and J. C. Langford (2000). Science 290 (5500), 2319-2323. Website.
2011
A tutorial introuction to Bayesian models of cognitive development. Perfors, A., Tenenbaum, J. B., Griffiths, T. L.,and Xu, F. (in press) Cognition.
The learnability of abstract syntactic principles. Perfors, A, Tenenbaum, J. B. and Regier, T. (in press). Cognition.
Learning to learn causal models. Kemp, C., Goodman, N. & Tenenbaum, J. (in press). Cognitive Science.
Learning a theory of causality. N. D. Goodman, T. D. Ullman, and J. B. Tenenbaum (in press). Psychological Review.
Three ideal observer models for rule learning in simple languages. Frank, M. C. & Tenenbaum, J. B. (in press). Cognition. Code package.
Probabilistic models of cognition: Exploring representations and inductive biases. Griffiths, T. L., Chater, N., Kemp, C., Perfors, A., & Tenenbaum, J. B. (in press). Trends in Cognitive Sciences.
How to Grow a Mind: Statistics, Structure, and Abstraction. Tenenbaum, J. B., Kemp, C., Griffiths, T. L., and Goodman, N. D. (2011). Science 331 (6022), 1279-1285. Supporting Online Material.
Pure reasoning in 12-month-old infants as probabilistic inference. Teglas, E., Vul, E., Girotto, V., Gonzalez, M., Tenenbaum, J. B., and Bonatti, L. L. (2011). Science 332, 1054-1059. Supporting Online Material.
Theory acquisition as stochastic search. T. D. Ullman, N. D. Goodman and J. B. Tenenbaum (2010). Proceedings of the Thirty-Second Annual Conference of the Cognitive Science Society.
2010
Variability, negative evidence, and the acquisition of verb argument constructions. . Perfors, A. F, Wonnacott, E., & Tenenbaum, J.B. (in press). Journal of Child Langauge.
Help or hinder: Bayesian models of social goal inference. Ullman, T.D., Baker, C.L., Macindoe, O., Evans, O., Goodman, N.D., & Tenenbaum, J.B. (2010). Advances in Neural Information Processing Systems (Vol. 22, pp. 1874-1882).
The structure and dynamics of scientific theories: a hierarchical Bayesian perspective. L. Henderson, N. D. Goodman, J. B. Tenenbaum and J. F. Woodward. Phil. Sci. 77 (2), 172-200 (2010).
2009
Action understanding as inverse planning. Baker, C. L., Saxe, R., & Tenenbaum, J. B. (2009). Cognition, 113, 329-349. Supplementary material.
Theory-based causal induction. Griffiths, T. L., & Tenenbaum, J. B. (2009). Psychological Review, 116, 661-716.
Structured statistical models of inductive reasoning. Kemp, C. and Tenenbaum, J. B. (2009). Psychological Review, 116(1), 20-58.
Using speakers' referential intentions to model early cross-situational word learning. Frank, M. C., Goodman, N. D., and Tenenbaum, J. B. (2009). Psychological Science 20, 578-585.
Exact and approximate sampling by systematic stochastic search. Mansinghka, V. K., Roy, D. M., Jonas, E., and Tenenbaum, J. B. (2009). AISTATS 2009.
Cause and Intent: Social Reasoning in Causal Learning. Goodman, N.D., Baker, C.L., & Tenenbaum, J.B. (2009). In Proceedings of the Thirty-First Annual Conference of the Cognitive Science Society (pp. 2759-2764).
Explaining human multiple object tracking as resource-constrained approximate inference in a dynamic probabilistic model. . E. Vul, M. C. Frank, J. B. Tenenbaum, and G. Alvarez (2009). Advances in Neural Information Processing Systems 21.
2008
Inductive reasoning about causally transmitted properties. Shafto, P., Kemp, C., Baraff, E. R., Coley, J., and Tenenbaum, J. B. (2008). Cognition, 109, 175-192.
A rational analysis of rule-based concept learning. N. D. Goodman, J. B. Tenenbaum, J. Feldman, and T. L. Griffiths (2008). Cognitive Science, 32:1, 108-154.
The discovery of structural form. Kemp, C. and Tenenbaum, J. B. (2008). Proceedings of the National Academy of Sciences. 105(31), 10687-10692. Supporting information. Commentary by K. J. Holyoak. Code and data sets.
Bayesian models of cognition. Griffiths, T. L., Kemp, C., and Tenenbaum, J. B. (2008). In Ron Sun (ed.), Cambridge Handbook of Computational Cognitive Modeling. Cambridge University Press.
Compositionality in rational analysis: Grammar-based induction for concept learning. In M. Oaksford and N. Chater (Eds.). Goodman, N. D., Tenenbaum, J. B., Griffiths, T. L., & Feldman, J. (2008). The probabilistic mind: Prospects for rational models of cognition. Oxford: Oxford University Press.
Church: a language for generative models. Goodman, N. D., Mansinghka, V. K., Roy, D., Bonawitz, K., and Tenenbaum, J. B. (2008). Uncertainty in Artificial Intelligence 2008.
Modeling semantic cognition as logical dimensionality reduction. Y. Katz, N. D. Goodman, K. Kersting, C. Kemp, and J. B. Tenenbaum (2008). Proceedings of the Thirtieth Annual Conference of the Cognitive Science Society.
Theory-based social goal inference. Baker, C.L., Goodman, N.D., & Tenenbaum, J.B. (2008). In Proceedings of the Thirtieth Annual Conference of the Cognitive Science Society (pp. 1447-1452).
A Bayesian framework for cross-situational word-learning. M. C. Frank, N. D. Goodman, and J. B. Tenenbaum (2008). Advances in Neural Information Processing Systems 20.
Learning and using relational theories. C. Kemp, N. D. Goodman, and J. B. Tenenbaum (2008). Advances in Neural Information Processing Systems 20.
2007
Theory-based Bayesian models of inductive reasoning. Tenenbaum, J. B., Kemp, C., and Shafto, P. (2007). In Feeney, A. & Heit, E. (eds.), Inductive reasoning. Cambridge University Press.
Causal inference in multisensory perception. Kording, K. P., Beierholm, U., Ma, W. J., Quartz, S., Tenenbaum, J. B., Shams, L. (2007). PLoS ONE. September 2007, Issue 9, e943.
The role of causality in judgment under uncertainty. Krynski, T. R. and Tenenbaum, J. B. (2007). Journal of Experimental Psychology: General 136(3), 430-450.
The dynamics of memory are a consequence of optimal adaptation to a changing body. Kording, K. P., Tenenbaum, J. B., and Shadmehr, R. (2007). Nature Neuroscience 10(6), 779-786.
Goal inference as inverse planning. Baker, C. L., Tenenbaum, J. B., and Saxe, R. R. (2007). Proceedings of the Twenty-Ninth Annual Conference of the Cognitive Science Society (pp. 779-784).
Modeling human performance in statistical word segmentation. Frank, M., Goldwater, S., Griffiths, T. L., Mansinghka, V. K., and Tenenbaum, J. B. (2007). Proceedings of the Twenty-Ninth Annual Conference of the Cognitive Science Society.
A rational analysis of rule-based concept learning. Goodman, N. D., Griffiths, T. L., Feldman, J., and Tenenbaum, J. B. (2007). Proceedings of the Twenty-Ninth Annual Conference of the Cognitive Science Society.
Learning grounded causal models. Goodman, N. D., Mansignhka, V. K., and Tenenbaum, J. B. (2007). Proceedings of the Twenty-Ninth Annual Conference of the Cognitive Science Society. [2007 Cognitive Science Computational Modeling Prize, Perception and Action category.]
Learning causal schemata. Kemp, C., Goodman, N. D., and Tenenbaum, J. B. (2007). Proceedings of the Twenty-Ninth Annual Conference of the Cognitive Science Society. [2007 Cognitive Science Computational Modeling Prize, Higher-Level Cognition category.]
Discovering syntactic hierarchies. Savova, V., Roy, D., Schmidt, L., and Tenenbaum, J. B. (2007). Proceedings of the Twenty-Ninth Annual Conference of the Cognitive Science Society.
Parametric embedding for class visualization. Iwata, T., Saito, K., Ueda, N., Stromsten, S., Griffiths, T. L., and Tenenbaum, J. B. (2007). Neural Computation 19, 2536-2556.
Learning annotated hierarchies from relational data. Roy, D., Kemp, C., Mansinghka, V., and Tenenbaum, J. B. (2007). Advances in Neural Information Processing Systems 19.
Combining causal and similarity-based reasoning. Kemp, C., Shafto, P., Berke, A., and Tenenbaum, J. B. (2007). Advances in Neural Information Processing Systems 19. [Honorable mention, Outstanding Student Paper award.]
Multiple timescales and uncertainty in motor adaptation. Kording, K., Tenenbaum, J. B., and Shadmehr, R. (2007). Advances in Neural Information Processing Systems 19.
Causal inference in sensorimotor integration. Kording, K. and Tenenbaum, J. B. (2007). Advances in Neural Information Processing Systems 19.
AClass: An online algorithm for generative classification. Mansinghka, V. K., Roy, D. M., Rifkin, R., and Tenenbaum, J. B. (2007). Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS07).
Word learning as Bayesian inference. Xu, F. and Tenenbaum, J. B. (2007). Psychological Review 114(2).
Topics in semantic representation. Griffiths, T. L., Steyvers, M., and Tenenbaum, J. B. (2007). Psychological Review 114(2).
Bayesian networks, Bayesian learning, and cognitive development. Gopnik, A. and Tenenbaum, J. B. (2007). Developmental Science 10(3), 281-287.
Sensitivity to sampling in Bayesian word learning. Xu, F. and Tenenbaum, J. B. (2007). Developmental Science 10(3), 288-297.
Learning overhypotheses with hierarchical Bayesian models. Kemp, C., Perfors, A., and Tenenbaum, J. B. (2007). Developmental Science 10(3), 307-321.
From mere coincidences to meaningful discoveries. Griffiths, T. L. and Tenenbaum, J. B. (2007). Cognition 103(2), 180-226.
Intuitive theories as grammars for causal inference. Tenenbaum, J.B., Griffiths, T. L., and Niyogi, S. (2007). In Gopnik, A., & Schulz, L. (eds.), Causal learning: Psychology, philosophy, and computation. Oxford University Press.
Two proposals for causal grammars. Griffiths, T. L. and Tenenbaum, J. B. (2007). In Gopnik, A., & Schulz, L. (eds.), Causal learning: Psychology, philosophy, and computation. Oxford University Press.
2006
Optimal predictions in everyday cognition. Griffiths, T. L. and Tenenbaum, J. B. (2006). Psychological Science 17(9), 767-773. Article in The Economist
Statistics and the Bayesian mind. Griffiths, T. L. and Tenenbaum, J. B. (2006). Significance 3(3), 130-133.
Theory-based Bayesian models of inductive learning and reasoning. Tenenbaum, J. B., Griffiths, T. L., and Kemp, C. (2006). Trends in Cognitive Sciences, 10(7), 309-318.
Probabilistic models of cognition: Conceptual foundations. Chater, N., Tenenbaum, J. B., and Yuille, A. (2006). Trends in Cognitive Sciences, 10(7), 287-291.
Unsupervised topic modelling for multi-party spoken discourse. Purver, M., Kording, K. P., Griffiths, T. L., & Tenenbaum, J. B. (2006). Proceedings of Coling/ACL 2006.
Structured priors for structure learning. Mansinghka, V. K., Kemp, C., Tenenbaum, J. B., and Griffiths, T. L. (2006). Proceedings of the Twenty-Second Conference on Uncertainty in Artificial Intelligence (UAI 2006).
Learning systems of concepts with an infinite relational model. Kemp, C., Tenenbaum, J. B., Griffiths, T. L., Yamada, T., and Ueda, N. (2006). Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-06). IRM Code
Learning cross-cutting systems of categories. Shafto, P. Kemp, C., Mansignhka, V., Gordon, M., and Tenenbaum, J. B. (2006). Proceedings of the Twenty-Eighth Annual Conference of the Cognitive Science Society.
Poverty of the Stimulus? A rational approach. Perfors, A., Regier, T. and Tenenbaum, J. B. (2006). Proceedings of the Twenty-Eighth Annual Conference of the Cognitive Science Society.
Nonsense and sensibility: Inferring unseen possibilities. Schmidt, L. A., Kemp, C., and Tenenbaum, J. B. (2006). Proceedings of the Twenty-Eighth Annual Conference of the Cognitive Science Society.
Learning overhypotheses. Kemp, C., Perfors, A. and Tenenbaum, J. B. (2006). Proceedings of the Twenty-Eighth Annual Conference of the Cognitive Science Society.
Intuitive theories of mind: A rational approach to false belief. Goodman, N. D., Baker, C. L., Bonawitz, E. B., Mansinghka, V. K, Gopnik, A., Wellman, H., Schulz, L. & Tenenbaum, J. B. (2006). Proceedings of the Twenty-Eighth Annual Conference of the Cognitive Science Society (pp. 1382-1387).
Bayesian models of human action understanding. C. L. Baker, J. B. Tenenbaum, R. R. Saxe (2006). Advances in Neural Information Processing Systems 18 (pp. 99-106).
2005
Parametric Embedding for Class Visualization. T. Iwata, K. Saito, N. Ueda, S. Stromsten, T. L. Griffiths, J. B. Tenenbaum (2005). Advances in Neural Information Processing Systems 17.
Context-sensitive induction. Shafto, P., Kemp, C., Baraff, L., Coley, J., and Tenenbaum, J. B. (2005). Proceedings of the Twenty-Seventh Annual Conference of the Cognitive Science Society.
Word learning as Bayesian inference: Evidence from preschoolers. Xu, F. and Tenenbaum, J. B. (2005). Proceedings of the Twenty-Seventh Annual Conference of the Cognitive Science Society.
Integrating topics and syntax. T. L. Griffiths, M. Steyvers, D. Blei, and J. B. Tenenbaum (2005). Advances in Neural Information Processing Systems 17.
The large-scale structure of semantic networks: statistical analyses and a model of semantic growth. M. Steyvers, J. B. Tenenbaum (2005), Cognitive Science, 29(1).
A generative theory of similarity. Kemp, C., Bernstein, A., and Tenenbaum, J. B. (2005). Proceedings of the Twenty-Seventh Annual Conference of the Cognitive Science Society.
Secret agents: inferences about hidden causes by 10- and 12-month-old infants. Saxe, R., Tenenbaum, J.B., and Carey, S. (2005). Psychological Science 16(12), 995-1001.
Structure and strength in causal induction.
Griffiths, T.L., & Tenenbaum, J.B. (2005). Cognitive Psychology 51, 334-384.
(This paper was formerly titled "Elemental causal induction.")
MATLAB code for computing causal support.
2004
Learning domain structures. Kemp, C. S., Perfors, A., and Tenenbaum, J. B. (2004). Proceedings of the Twenty-Sixth Annual Conference of the Cognitive Science Society.
Discovering latent classes in relational data. C. Kemp, T. L. Griffiths, & J. B. Tenenbaum (2004). MIT AI Memo 2004-019.
Semi-supervised learning with trees. Kemp, C., Griffiths, T. L, Stromsten, S., and Tenenbaum, J. B. (2004). Advances in Neural Information Processing Systems 16.
Hierarchical topic models and the nested Chinese restaurant process. D. Blei, T. L. Griffiths, M. I. Jordan, and J. B. Tenenbaum (2004). Advances in Neural Information Processing Systems 16. [Best Student Paper, NIPS 2003, Synthetic Systems Category.]
From algorithmic to subjective randomness. Griffiths, T. L. and Tenenbaum, J. B. (2004). Advances in Neural Information Processing Systems 16. [Best Student Paper, NIPS 2003, Natural Systems Category.]
Children's causal inferences from indirect evidence: Backwards blocking and Bayesian reasoning in preschoolers. D. Sobel, J. B. Tenenbaum, A. Gopnik (2004), Cognitive Science, 28, 303-333.
Using physical theories to infer hidden causal structure. Griffiths, T.L., Baraff, E.R., & Tenenbaum, J.B. (2004). Proceedings of the Twenty-Sixth Annual Conference of the Cognitive Science Society. [Marr Prize for Best Student Paper, Honorable Mention, Cognitive Science 2004.]
2003
Learning style translation for the lines of a drawing. W.T. Freeman, J.B. Tenenbaum, E. Pasztor (2003). ACM Transactions on Graphics 22 (1), January 2003, 33-46. (uncorrected proofs - SMALL pdf)
Theory-based induction. Kemp, C. S. and Tenenbaum, J. B. (2003). Proceedings of the Twenty-Fifth Annual Conference of the Cognitive Science Society.
The role of causal models in reasoning under uncertainty. Krynski, T. R. and Tenenbaum, J. B. (2003). Proceedings of the Twenty-Fifth Annual Conference of the Cognitive Science Society.
V1 neurons signal acquisition of an internal representation of stimulus location. Sharma, J., Dragoi, V., Tenenbaum, J. B., Miller, E. K., and Sur, M. (2003). Science, 300, 1758-1763.
Probability, algorithmic complexity, and subjective randomness. Griffiths, T. L. and Tenenbaum, J. B. (2003). Proceedings of the Twenty-Fifth Annual Conference of the Cognitive Science Society.
Learning causal laws. Tenenbaum, J. B. and Niyogi, S. (2003). Proceedings of the Twenty-Fifth Annual Conference of the Cognitive Science Society.
Dynamical causal learning. Danks, D., Griffiths, T.L., & Tenenbaum, J.B. (2003). Advances in Neural Information Processing Systems 15. Becker, S., Thrun, S., and Obermayer. (eds). Cambridge, MIT Press, 2003, 67-74.
Inferring causal networks from observations and interventions. M. Steyvers, J. B. Tenenbaum, E. J. Wagenmakers, B. Blum (2003), Cognitive Science 27: 453-489.
Theory-based causal inference. J. B. Tenenbaum, T. L. Griffiths (2003), Advances in Neural Information Processing Systems 15. Becker, S., Thrun, S., and Obermayer. (eds). Cambridge, MIT Press, 2003, 35-42.
2002
The Isomap Algorithm and Topological Stability. M. Balasubramanian, E. L. Shwartz, J. B. Tenenbaum, V. de Silva, and J. C. Langford (2002). Science Jan 4 2002: 7.
Global versus local methods in nonlinear dimensionality reduction. V. de Silva, J. B. Tenenbaum (2002). Advances in Neural Information Processing Systems 15. S. Becker, S., Thrun, S., and Obermayer, K. (eds). Cambridge, MIT Press, 2002, 705-712.
Unsupervised learning of curved manifolds. V. de Silva, J.B. Tenenbaum (2002). In D.D. Denison, M. H. Hansen, C. C. Holmes, B. Mallick and B. Yu (eds.), Nonlinear Estimation and Classification , Springer-Verlag, New York, 453-466.
Bayesian models of inductive generalization. N. Sanjana, J. B. Tenenbaum (2002), Advances in Neural Information Processing Systems 15. Becker, S., Thrun, S., Obermayer, K. (eds). Cambridge, MIT Press, 2002, 51-58. [Best Student Paper, Honorable Mention, NIPS 2001.]
2001
Generalization, similarity, and Bayesian inference. J. B. Tenenbaum, T. L. Griffiths (2001), Behavioral and Brain Sciences, 24 pp. 629-641.
Some specifics about generalization. J. B. Tenenbaum, T. L. Griffiths (2001), Behavioral and Brain Sciences, 24, pages 772-778.
The rational basis of representativeness. J. B. Tenenbaum, T. L. Griffiths (2001), 23rd Annual Conference of the Cognitive Science Society. 1036-1041.
Randomness and coincidences: Reconciling intuition and probability theory. T. L. Griffiths, J. B. Tenenbaum (2001), 23rd Annual Conference of the Cognitive Science Society. 370-375. Article in Psychology Today (single-page view)
Structure learning in human causal induction. J. B. Tenenbaum, T. L. Griffiths (2001), Advances in Neural Information Processing Systems 13. Leen, T., Dietterich, T., and Tresp, V., Cambridge, MIT Press, 2001, 59-65. (postscript)
2000
A global geometric framework for nonlinear dimensionality reduction. J. B. Tenenbaum, V. De Silva and J. C. Langford (2000). Science 290 (5500), 2319-2323. Website
Separating style and content with bilinear models. J. B. Tenenbaum, W. T. Freeman (2000). Neural Computation 12 (6), 1247-1283. [Conference version received the Outstanding Paper Award at IEEE CVPR 1997.]
Rules and similarity in concept learning. J. B. Tenenbaum (2000), Advances in Neural Information Processing Systems 12. Solla, S., Leen, T. and Muller, K. (eds). Cambridge, MIT Press, 2000, 59-65. (postscript)
Word learning as Bayesian inference. J. B. Tenenbaum, F. Xu (2000), Proceedings of the 22nd Annual Conference of the Cognitive Science Society (postscript)
Teacakes, trains, toxins, and taxicabs: A Bayesian account of predicting the future. T. L. Griffiths, J. B. Tenenbaum (2000), Proceedings of the 22nd Annual Conference of the Cognitive Science Society. 202-207. (postscript)
1999 and before
Bayesian modeling of human concept learning. J. B. Tenenbaum (1999), Advances in Neural Information Processing Systems 11. Kearns, M., Solla, S., and Cohn, D. (eds). Cambridge, MIT Press, 1999, 59-65. (postscript)
A Bayesian Framework for Concept Learning. J. B. Tenenbaum, Ph.D. Thesis, MIT, 1999
Mapping a manifold of perceptual observations. J. B. Tenenbaum (1998). Advances in Neural Information Processing Systems 10. Jordan, M., Kearns, M., and Solla, S. (eds). Cambridge, MIT Press, 1998, 682-688. (postscript)
Learning the structure of similarity. J. B. Tenenbaum (1995), Advances in Neural Information Processing Systems 8. Toretzky, D., Mozer, M., and Hasselmo, M. (eds). Cambridge, MIT Press, 1995, 3-9. (postscript)
Nonlinear dimensionality reduction
Parametric Embedding for Class Visualization. T. Iwata, K. Saito, N. Ueda, S. Stromsten, T. L. Griffiths, J. B. Tenenbaum (2005). Advances in Neural Information Processing Systems 17.
The Isomap Algorithm and Topological Stability. M. Balasubramanian, E. L. Shwartz, J. B. Tenenbaum, V. de Silva, and J. C. Langford (2002). Science Jan 4 2002: 7.
Global versus local methods in nonlinear dimensionality reduction. V. de Silva, J. B. Tenenbaum (2002). Advances in Neural Information Processing Systems 15. S. Becker, S., Thrun, S., and Obermayer, K. (eds). Cambridge, MIT Press, 2002, 705-712.
Unsupervised learning of curved manifolds. V. de Silva, J.B. Tenenbaum (2002). In D.D. Denison, M. H. Hansen, C. C. Holmes, B. Mallick and B. Yu (eds.), Nonlinear Estimation and Classification , Springer-Verlag, New York, 453-466.
A global geometric framework for nonlinear dimensionality reduction. J. B. Tenenbaum, V. De Silva and J. C. Langford (2000). Science 290 (5500), 2319-2323. Website
Mapping a manifold of perceptual observations. J. B. Tenenbaum (1998). Advances in Neural Information Processing Systems 10. Jordan, M., Kearns, M., and Solla, S. (eds). Cambridge, MIT Press, 1998, 682-688. (postscript)
Separating style and content
Learning style translation for the lines of a drawing. W.T. Freeman, J.B. Tenenbaum, E. Pasztor (2003). ACM Transactions on Graphics 22 (1), January 2003, 33-46. (uncorrected proofs - SMALL pdf)
Separating style and content with bilinear models. J. B. Tenenbaum, W. T. Freeman (2000). Neural Computation 12 (6), 1247-1283. [Conference version received the Outstanding Paper Award at IEEE CVPR 1997.]
Concept learning and generalization
Context-sensitive induction. Shafto, P., Kemp, C., Baraff, L., Coley, J., and Tenenbaum, J. B. (2005). Proceedings of the Twenty-Seventh Annual Conference of the Cognitive Science Society.
Learning domain structures. Kemp, C. S., Perfors, A., and Tenenbaum, J. B. (2004). Proceedings of the Twenty-Sixth Annual Conference of the Cognitive Science Society.
Discovering latent classes in relational data. C. Kemp, T. L. Griffiths, & J. B. Tenenbaum (2004). MIT AI Memo 2004-019.
Semi-supervised learning with trees. Kemp, C., Griffiths, T. L, Stromsten, S., and Tenenbaum, J. B. (2004). Advances in Neural Information Processing Systems 16.
Theory-based induction. Kemp, C. S. and Tenenbaum, J. B. (2003). Proceedings of the Twenty-Fifth Annual Conference of the Cognitive Science Society.
Bayesian models of inductive generalization. N. Sanjana, J. B. Tenenbaum (2002), Advances in Neural Information Processing Systems 15. Becker, S., Thrun, S., Obermayer, K. (eds). Cambridge, MIT Press, 2002, 51-58. [Best Student Paper, Honorable Mention, NIPS 2001.]
Rules and similarity in concept learning. J. B. Tenenbaum (2000), Advances in Neural Information Processing Systems 12. Solla, S., Leen, T. and Muller, K. (eds). Cambridge, MIT Press, 2000, 59-65. (postscript)
Bayesian modeling of human concept learning. J. B. Tenenbaum (1999), Advances in Neural Information Processing Systems 11. Kearns, M., Solla, S., and Cohn, D. (eds). Cambridge, MIT Press, 1999, 59-65. (postscript)
A Bayesian Framework for Concept Learning. J. B. Tenenbaum, Ph.D. Thesis, MIT, 1999.
Learning and Representing Word Meanings
Word learning as Bayesian inference: Evidence from preschoolers. Xu, F. and Tenenbaum, J. B. (2005). Proceedings of the Twenty-Seventh Annual Conference of the Cognitive Science Society.
Integrating topics and syntax. T. L. Griffiths, M. Steyvers, D. Blei, and J. B. Tenenbaum (2005). Advances in Neural Information Processing Systems 17.
The large-scale structure of semantic networks: statistical analyses and a model of semantic growth. M. Steyvers, J. B. Tenenbaum (2005), Cognitive Science, 29(1).
Hierarchical topic models and the nested Chinese restaurant process. D. Blei, T. L. Griffiths, M. I. Jordan, and J. B. Tenenbaum (2004). Advances in Neural Information Processing Systems 16. [Best Student Paper, NIPS 2003, Synthetic Systems Category.]
Word learning as Bayesian inference. J. B. Tenenbaum, F. Xu (2000), Proceedings of the 22nd Annual Conference of the Cognitive Science Society (postscript)
Learning and similarity
A generative theory of similarity. Kemp, C., Bernstein, A., and Tenenbaum, J. B. (2005). Proceedings of the Twenty-Seventh Annual Conference of the Cognitive Science Society.
Generalization, similarity, and Bayesian inference. J. B. Tenenbaum, T. L. Griffiths (2001), Behavioral and Brain Sciences, 24 pp. 629-641.
Some specifics about generalization. J. B. Tenenbaum, T. L. Griffiths (2001), Behavioral and Brain Sciences, 24, pages 772-778.
Learning the structure of similarity. J. B. Tenenbaum (1995), Advances in Neural Information Processing Systems 8. Toretzky, D., Mozer, M., and Hasselmo, M. (eds). Cambridge, MIT Press, 1995, 3-9. (postscript)
Probabilistic reasoning
From mere coincidences to meaningful discoveries. Griffiths, T. L. and Tenenbaum, J. B. (in press). Cognition.
Optimal predictions in everyday cognition. Griffiths, T. L. and Tenenbaum, J. B. (in press). Psychological Science. Article in The Economist
From algorithmic to subjective randomness. Griffiths, T. L. and Tenenbaum, J. B. (2004). Advances in Neural Information Processing Systems 16. [Best Student Paper, NIPS 2003, Natural Systems Category.]
The role of causal models in reasoning under uncertainty. Krynski, T. R. and Tenenbaum, J. B. (2003). Proceedings of the Twenty-Fifth Annual Conference of the Cognitive Science Society.
V1 neurons signal acquisition of an internal representation of stimulus location. Sharma, J., Dragoi, V., Tenenbaum, J. B., Miller, E. K., and Sur, M. (2003). Science, 300, 1758-1763.
Probability, algorithmic complexity, and subjective randomness. Griffiths, T. L. and Tenenbaum, J. B. (2003). Proceedings of the Twenty-Fifth Annual Conference of the Cognitive Science Society.
The rational basis of representativeness. J. B. Tenenbaum, T. L. Griffiths (2001), 23rd Annual Conference of the Cognitive Science Society. 1036-1041.
Randomness and coincidences: Reconciling intuition and probability theory. T. L. Griffiths, J. B. Tenenbaum (2001), 23rd Annual Conference of the Cognitive Science Society. 370-375. Article in Psychology Today
Teacakes, trains, toxins, and taxicabs: A Bayesian account of predicting the future. T. L. Griffiths, J. B. Tenenbaum (2000), Proceedings of the 22nd Annual Conference of the Cognitive Science Society. 202-207. (postscript)
Causal learning and inference
Intuitive theories as grammars for causal inference. Tenenbaum, J.B., Griffiths, T. L., and Niyogi, S. (2007). In Gopnik, A., & Schulz, L. (eds.), Causal learning: Psychology, philosophy, and computation. Oxford University Press.
Two proposals for causal grammars. Griffiths, T. L. and Tenenbaum, J. B. (2007). In Gopnik, A., & Schulz, L. (eds.), Causal learning: Psychology, philosophy, and computation. Oxford University Press.
Secret agents: inferences about hidden causes by 10- and 12-month-old infants. Saxe, R., Tenenbaum, J.B., and Carey, S. (2005). Psychological Science 16(12), 995-1001.
Structure and strength in causal induction. Griffiths, T.L., & Tenenbaum, J.B. (2005). Cognitive Psychology 51(4), 285-386.
(MATLAB code for computing causal support)
Children's causal inferences from indirect evidence: Backwards blocking and Bayesian reasoning in preschoolers. D. Sobel, J. B. Tenenbaum, A. Gopnik (2004), Cognitive Science, 28, 303-333.
Using physical theories to infer hidden causal structure. Griffiths, T.L., Baraff, E.R., & Tenenbaum, J.B. (2004). Proceedings of the Twenty-Sixth Annual Conference of the Cognitive Science Society. [Marr Prize for Best Student Paper, Honorable Mention, Cognitive Science 2004.]
Learning causal laws. Tenenbaum, J. B. and Niyogi, S. (2003). Proceedings of the Twenty-Fifth Annual Conference of the Cognitive Science Society.
Dynamical causal learning. Danks, D., Griffiths, T.L., & Tenenbaum, J.B. (2003). Advances in Neural Information Processing Systems 15. Becker, S., Thrun, S., and Obermayer. (eds). Cambridge, MIT Press, 2003, 67-74.
Inferring causal networks from observations and interventions. M. Steyvers, J. B. Tenenbaum, E. J. Wagenmakers, B. Blum (2003), Cognitive Science 27: 453-489.
Theory-based causal inference. J. B. Tenenbaum, T. L. Griffiths (2003), Advances in Neural Information Processing Systems 15. Becker, S., Thrun, S., and Obermayer. (eds). Cambridge, MIT Press, 2003, 35-42.
Structure learning in human causal induction. J. B. Tenenbaum, T. L. Griffiths (2001), Advances in Neural Information Processing Systems 13. Leen, T., Dietterich, T., and Tresp, V., Cambridge, MIT Press, 2001, 59-65. (postscript)
Theory of mind
Help or hinder: Bayesian models of social goal inference. Ullman, T.D., Baker, C.L., Macindoe, O., Evans, O., Goodman, N.D., & Tenenbaum, J.B. (2010). Advances in Neural Information Processing Systems (Vol. 22, pp. 1874-1882).
Action understanding as inverse planning. Baker, C. L., Saxe, R., & Tenenbaum, J. B. (2009). Cognition, 113, 329-349. Supplementary material.
Cause and Intent: Social Reasoning in Causal Learning. Goodman, N.D., Baker, C.L., & Tenenbaum, J.B. (2009). In Proceedings of the Thirty-First Annual Conference of the Cognitive Science Society (pp. 2759-2764).
Theory-based Social Goal Inference. Baker, C.L., Goodman, N.D., & Tenenbaum, J.B. (2008). In Proceedings of the Thirtieth Annual Conference of the Cognitive Science Society (pp. 1447-1452).
Goal inference as inverse planning. Baker, C. L., Tenenbaum, J. B., and Saxe, R. R. (2007). Proceedings of the Twenty-Ninth Annual Conference of the Cognitive Science Society (pp. 779-784).
Intuitive theories of mind: A rational approach to false belief. Goodman, N. D., Baker, C. L., Bonawitz, E. B., Mansinghka, V. K, Gopnik, A., Wellman, H., Schulz, L. & Tenenbaum, J. B. (2006). Proceedings of the Twenty-Eighth Annual Conference of the Cognitive Science Society (pp. 1382-1387).
Bayesian models of human action understanding. Baker, C. L, Tenenbaum, J. B. & Saxe, R. R. (2006). Advances in Neural Information Processing Systems 18 (pp. 99-106).