Topic |
Readings |
Introduction |
- Probabilistic machine learning and artificial intelligence - Ghahramani - Nature (2015)
- Deep learning - LeCun, Bengio & Hinton - Nature (2015)
- How to grow a mind: Statistics, structure, and abstraction - Tenenbaum et al. - Science (2011)
- Building machines that learn and think like people - Lake et al. - Science (2016)
- Computational rationality: A converging paradigm for intelligence in brains, minds, and machines - Gershman, Horvitz & Tenenbaum - Science (2015)
|
Basic Bayesian Cognition |
- AIMA, Chapter 13: Quantifying uncertainty - Russell & Norvig (2009)
- From mere coincidences to meaningful discoveries - Griffiths & Tenenbaum - Cognition (2007)
- Online learning of symbolic concepts - Thaker, Tenenbaum & Gershman - J. Mathematical Psychology (2017)
- (Optional) Data analysis: A Bayesian tutorial - Sivia & Skilling (2006)
- (Optional) Judgement under uncertainty: Heuristics and biases - Tversky & Kahneman - Science (1974)
|
Bayesian Inference and Bayesian Concept Learning |
- Machine Learning, Chapter 6: Bayesian learning - Mitchell (1997)
- Rules and similarity in concept learning - Tenenbaum - NIPS (2000)
- Word learning as Bayesian inference - Xu & Tenenbaum - Psychological Review (2007)
- Sensitivity to sampling in Bayesian word learning - Xu & Tenenbaum - Developmental Science (2007)
|
Human Cognition as Statistical Inference: Computational Theories and Rational Analysis |
- Vision: A computational investigation into the human representation and processing of visual information, Chapter 1 - Marr (1982)
- Ten years of the rational analysis of cognition - Chater & Oaksford - Trends in Cognitive Sciences (1999)
- Optimal predictions in everyday cognition - Griffiths & Tenenbaum - Psychological Science (2006)
|
Graphical Models and Bayes Nets |
- AIMA, Chapter 14: Probabilistic reasoning - Russell & Norvig (2009)
- Bayesian networks without tears - Charniak - AI Magazine (1991)
- (Optional) The appeal of parallel distributed processing - McClelland, Rumelhart & Hinton
- (Optional) Illusory inferences about probabilities - Johnson-Laird & Savary - Acta Psychologica (1996)
- (Optional) The logical primitives of thought - Piantadosi, Tenenbaum & Goodman - Psychological Review (2016)
|
Probabilistic Programming Languages |
- Probabilistic models of cognition, 2nd edition - Goodman & Tenenbaum (2016)
- The design and implementation of probabilistic programming languages - Goodman & Stuhlmuller (2015
|
Approximate Probabilistic Inference: MCMC, Gibbs Sampling, Particle Filtering |
- Introducing Markov Chain Monte Carlo - Gilks, Richardson & Spiegelhalter (1996)
- AIMA, Chapter 14: Probabilistic reasoning - Russell & Norvig (2009)
- Explaining human multiple object tracking as resource-constrained approximate inference in a dynamic probabilistic model - Vul et al. - NIPS (2009)
- Modeling the effects of memory on human online sentence processing with particle filters - Levy, Reali & Griffiths - NIPS (2009)
- Detecting and predicting changes - Brown & Steyvers - Cognitive Psychology (2009)
- Multistability and perceptual inference - Gershman, Vul & Tenenbaum - Neural Computation (2012)
|
Probabilistic Programs and Common Sense |
- Simulation as an engine for physical scene understanding - Battaglia, Hamrick & Tenenbaum - PNAS (2013)
|
Model Selection and the Bayesian Occam’s Razor |
- Ockham’s razor and Bayesian analysis - Jefferys & Berger - American Scientist (1992)
- Bayesian learning of visual chunks by human observers - Orban et al. - PNAS (2008)
- Bayesian theories of conditioning in a changing world - Courville, Daw & Touretzky - Trends in Cognitive Sciences (2006)
- (Optional) Structure and strength in causal induction - Griffiths & Tenenbaum - Cognitive Psychology (2005)
- (Optional) Occam’s razor - Rasmussen & Ghahramani - NIPS (2001)
|
Learning with Hierarchical Bayesian Models |
- Learning overhypotheses with hierarchical Bayesian models - Kemp, Perfors & Tenenbaum - Developmental Science (2007)
- One-shot learning with a hierarchical nonparametric Bayesian model - Salakhutdinov, Tenenbaum & Torralba - J. Machine Learning Research (2012)
- A tutorial on Bayesian nonparametric models - Gershman & Blei - J. Mathematical Psychology (2012)
- (Optional) Topics in semantic representation - Griffiths, Steyvers & Tenenbaum - Psychological Review (2007)
|
Probabilistic Models for Concept Learning and Categorization |
- On the genesis of abstract ideas - Posner & Keele - J. Experimental Psychology (1968)
- The adaptive nature of categorization - Anderson - Psychological Review (1991)
- Rational models: Alternative algorithms for category learning - Sanborn & Griffiths - Psychological Review (2010)
|
Models of Human Cognitive Development |
- Constraints on knowledge and cognitive development - Keil - Psychological Review (1981)
- Learning domain structures - Kemp, Perfors & Tenenbaum - Proc. Annual Meeting Cognitive Science Society (2004)
- Knowledge acquisition: Enrichment or conceptual change - Carey (1999)
- The role of theories in conceptual coherence - Murphy & Medin - (1985)
- Intuitive statistics by 8-month-old infants - Xu & Garcia - PNAS (2008)
- Pure reasoning in 12-month-old infants as probabilistic inference - Teglas et al. - Science (2011)
|
Planning and Decision Making |
- Action understanding as inverse planning - Baker, Saxe & Tenenbaum - Cognition (2009)
- A rational model of preference learning and choice prediction by children - Lucas et al. - NIPS (2009)
- Game Theory of Mind - Yoshida, Dolan & Friston - PLoS Computational Biology (2008)
- (Optional) Structure learning in human sequential decision-making - Acuna & Schrater - PLoS Computational Biology (2010)
|