How do humans come to know so much about the world from so little data? Even young children can infer the meanings of words, the hidden properties of objects, or the existence of causal relations from just one or a few relevant observations -- far outstripping the capabilities of conventional learning machines. How do they do it -- and how can we bring machines closer to these human-like learning abilities? I will argue that people's everyday inductive leaps can be understood in terms of (approximations to) probabilistic inference over generative models of the world. These models can have rich latent structure based on abstract knowledge representations, what cognitive psychologists have sometimes called "intuitive theories", "mental models", or "schemas". They also typically have a hierarchical structure supporting inference at multiple levels, or "learning to learn", where abstract knowledge may itself be learned from experience at the same time as it guides more specific generalizations from sparse data.
This talk will focus on models of learning and "learning to learn" about categories, word meanings and causal relations. I will show in each of these settings how human learners can balance the need for strongly constraining inductive biases -- necessary for rapid generalization -- with the flexibility to adapt to the structure of new environments, learning new inductive biases for which our minds could not have been pre-programmed. I will also discuss briefly how this approach extends to richer forms of knowledge, such as intuitive psychology and social inferences, or physical reasoning. Finally, I will raise some challenges for our current state of understanding about learning in the brain, and neurally inspired computational models.
Author Information
Josh Tenenbaum (MIT)
Josh Tenenbaum is an Associate Professor of Computational Cognitive Science at MIT in the Department of Brain and Cognitive Sciences and the Computer Science and Artificial Intelligence Laboratory (CSAIL). He received his PhD from MIT in 1999, and was an Assistant Professor at Stanford University from 1999 to 2002. He studies learning and inference in humans and machines, with the twin goals of understanding human intelligence in computational terms and bringing computers closer to human capacities. He focuses on problems of inductive generalization from limited data -- learning concepts and word meanings, inferring causal relations or goals -- and learning abstract knowledge that supports these inductive leaps in the form of probabilistic generative models or 'intuitive theories'. He has also developed several novel machine learning methods inspired by human learning and perception, most notably Isomap, an approach to unsupervised learning of nonlinear manifolds in high-dimensional data. He has been Associate Editor for the journal Cognitive Science, has been active on program committees for the CogSci and NIPS conferences, and has co-organized a number of workshops, tutorials and summer schools in human and machine learning. Several of his papers have received outstanding paper awards or best student paper awards at the IEEE Computer Vision and Pattern Recognition (CVPR), NIPS, and Cognitive Science conferences. He is the recipient of the New Investigator Award from the Society for Mathematical Psychology (2005), the Early Investigator Award from the Society of Experimental Psychologists (2007), and the Distinguished Scientific Award for Early Career Contribution to Psychology (in the area of cognition and human learning) from the American Psychological Association (2008).
More from the Same Authors
-
2019 Poster: Write, Execute, Assess: Program Synthesis with a REPL »
Kevin Ellis · Maxwell Nye · Yewen Pu · Felix Sosa · Josh Tenenbaum · Armando Solar-Lezama -
2019 Poster: ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models »
Andrei Barbu · David Mayo · Julian Alverio · William Luo · Christopher Wang · Dan Gutfreund · Josh Tenenbaum · Boris Katz -
2019 Poster: Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations »
Kevin Smith · Lingjie Mei · Shunyu Yao · Jiajun Wu · Elizabeth Spelke · Josh Tenenbaum · Tomer Ullman -
2019 Poster: Visual Concept-Metaconcept Learning »
Chi Han · Jiayuan Mao · Chuang Gan · Josh Tenenbaum · Jiajun Wu -
2019 Poster: Finding Friend and Foe in Multi-Agent Games »
Jack Serrino · Max Kleiman-Weiner · David Parkes · Josh Tenenbaum -
2019 Spotlight: Finding Friend and Foe in Multi-Agent Games »
Jack Serrino · Max Kleiman-Weiner · David Parkes · Josh Tenenbaum -
2018 Workshop: Modeling the Physical World: Learning, Perception, and Control »
Jiajun Wu · Kelsey Allen · Kevin Smith · Jessica Hamrick · Emmanuel Dupoux · Marc Toussaint · Josh Tenenbaum -
2018 Poster: Learning to Reconstruct Shapes from Unseen Classes »
Xiuming Zhang · Zhoutong Zhang · Chengkai Zhang · Josh Tenenbaum · Bill Freeman · Jiajun Wu -
2018 Poster: Learning to Infer Graphics Programs from Hand-Drawn Images »
Kevin Ellis · Daniel Ritchie · Armando Solar-Lezama · Josh Tenenbaum -
2018 Poster: Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction »
Kevin Ellis · Lucas Morales · Mathias Sablé-Meyer · Armando Solar-Lezama · Josh Tenenbaum -
2018 Oral: Learning to Reconstruct Shapes from Unseen Classes »
Xiuming Zhang · Zhoutong Zhang · Chengkai Zhang · Josh Tenenbaum · Bill Freeman · Jiajun Wu -
2018 Spotlight: Learning to Infer Graphics Programs from Hand-Drawn Images »
Kevin Ellis · Daniel Ritchie · Armando Solar-Lezama · Josh Tenenbaum -
2018 Spotlight: Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction »
Kevin Ellis · Lucas Morales · Mathias Sablé-Meyer · Armando Solar-Lezama · Josh Tenenbaum -
2018 Poster: Visual Object Networks: Image Generation with Disentangled 3D Representations »
Jun-Yan Zhu · Zhoutong Zhang · Chengkai Zhang · Jiajun Wu · Antonio Torralba · Josh Tenenbaum · Bill Freeman -
2018 Poster: Learning to Share and Hide Intentions using Information Regularization »
DJ Strouse · Max Kleiman-Weiner · Josh Tenenbaum · Matt Botvinick · David Schwab -
2018 Poster: Learning to Exploit Stability for 3D Scene Parsing »
Yilun Du · Zhijian Liu · Hector Basevi · Ales Leonardis · Bill Freeman · Josh Tenenbaum · Jiajun Wu -
2018 Poster: End-to-End Differentiable Physics for Learning and Control »
Filipe de Avila Belbute-Peres · Kevin Smith · Kelsey Allen · Josh Tenenbaum · J. Zico Kolter -
2018 Spotlight: End-to-End Differentiable Physics for Learning and Control »
Filipe de Avila Belbute-Peres · Kevin Smith · Kelsey Allen · Josh Tenenbaum · J. Zico Kolter -
2018 Poster: Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding »
Kexin Yi · Jiajun Wu · Chuang Gan · Antonio Torralba · Pushmeet Kohli · Josh Tenenbaum -
2018 Poster: 3D-Aware Scene Manipulation via Inverse Graphics »
Shunyu Yao · Tzu Ming Hsu · Jun-Yan Zhu · Jiajun Wu · Antonio Torralba · Bill Freeman · Josh Tenenbaum -
2018 Spotlight: Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding »
Kexin Yi · Jiajun Wu · Chuang Gan · Antonio Torralba · Pushmeet Kohli · Josh Tenenbaum -
2018 Poster: Flexible neural representation for physics prediction »
Damian Mrowca · Chengxu Zhuang · Elias Wang · Nick Haber · Li Fei-Fei · Josh Tenenbaum · Daniel Yamins -
2017 Workshop: Learning Disentangled Features: from Perception to Control »
Emily Denton · Siddharth Narayanaswamy · Tejas Kulkarni · Honglak Lee · Diane Bouchacourt · Josh Tenenbaum · David Pfau -
2017 Spotlight: Shape and Material from Sound »
Zhoutong Zhang · Qiujia Li · Zhengjia Huang · Jiajun Wu · Josh Tenenbaum · Bill Freeman -
2017 Spotlight: Scene Physics Acquisition via Visual De-animation »
Jiajun Wu · Erika Lu · Pushmeet Kohli · Bill Freeman · Josh Tenenbaum -
2017 Poster: Learning to See Physics via Visual De-animation »
Jiajun Wu · Erika Lu · Pushmeet Kohli · Bill Freeman · Josh Tenenbaum -
2017 Poster: Shape and Material from Sound »
Zhoutong Zhang · Qiujia Li · Zhengjia Huang · Jiajun Wu · Josh Tenenbaum · Bill Freeman -
2017 Poster: MarrNet: 3D Shape Reconstruction via 2.5D Sketches »
Jiajun Wu · Yifan Wang · Tianfan Xue · Xingyuan Sun · Bill Freeman · Josh Tenenbaum -
2017 Poster: Self-Supervised Intrinsic Image Decomposition »
Michael Janner · Jiajun Wu · Tejas Kulkarni · Ilker Yildirim · Josh Tenenbaum -
2017 Tutorial: Engineering and Reverse-Engineering Intelligence Using Probabilistic Programs, Program Induction, and Deep Learning »
Josh Tenenbaum · Vikash Mansinghka -
2016 Workshop: Intuitive Physics »
Adam Lerer · Jiajun Wu · Josh Tenenbaum · Emmanuel Dupoux · Rob Fergus -
2016 Poster: Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation »
Tejas Kulkarni · Karthik Narasimhan · Ardavan Saeedi · Josh Tenenbaum -
2016 Poster: Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling »
Jiajun Wu · Chengkai Zhang · Tianfan Xue · Bill Freeman · Josh Tenenbaum -
2016 Poster: Sampling for Bayesian Program Learning »
Kevin Ellis · Armando Solar-Lezama · Josh Tenenbaum -
2016 Poster: Probing the Compositionality of Intuitive Functions »
Eric Schulz · Josh Tenenbaum · David Duvenaud · Maarten Speekenbrink · Samuel J Gershman -
2015 Workshop: Black box learning and inference »
Josh Tenenbaum · Jan-Willem van de Meent · Tejas Kulkarni · S. M. Ali Eslami · Brooks Paige · Frank Wood · Zoubin Ghahramani -
2015 Poster: Softstar: Heuristic-Guided Probabilistic Inference »
Mathew Monfort · Brenden M Lake · Brenden Lake · Brian Ziebart · Patrick Lucey · Josh Tenenbaum -
2015 Poster: Deep Convolutional Inverse Graphics Network »
Tejas Kulkarni · William Whitney · Pushmeet Kohli · Josh Tenenbaum -
2015 Spotlight: Deep Convolutional Inverse Graphics Network »
Tejas Kulkarni · William Whitney · Pushmeet Kohli · Josh Tenenbaum -
2015 Poster: Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning »
Jiajun Wu · Ilker Yildirim · Joseph Lim · Bill Freeman · Josh Tenenbaum -
2015 Poster: Unsupervised Learning by Program Synthesis »
Kevin Ellis · Armando Solar-Lezama · Josh Tenenbaum -
2014 Workshop: 3rd NIPS Workshop on Probabilistic Programming »
Daniel Roy · Josh Tenenbaum · Thomas Dietterich · Stuart J Russell · YI WU · Ulrik R Beierholm · Alp Kucukelbir · Zenna Tavares · Yura Perov · Daniel Lee · Brian Ruttenberg · Sameer Singh · Michael Hughes · Marco Gaboardi · Alexey Radul · Vikash Mansinghka · Frank Wood · Sebastian Riedel · Prakash Panangaden -
2013 Workshop: Deep Learning »
Yoshua Bengio · Hugo Larochelle · Russ Salakhutdinov · Tomas Mikolov · Matthew D Zeiler · David Mcallester · Nando de Freitas · Josh Tenenbaum · Jian Zhou · Volodymyr Mnih -
2013 Poster: One-shot learning by inverting a compositional causal process »
Brenden M Lake · Russ Salakhutdinov · Josh Tenenbaum -
2013 Poster: Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs »
Vikash Mansinghka · Tejas D Kulkarni · Yura N Perov · Josh Tenenbaum -
2013 Oral: Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs »
Vikash Mansinghka · Tejas D Kulkarni · Yura N Perov · Josh Tenenbaum -
2011 Workshop: Challenges in Learning Hierarchical Models: Transfer Learning and Optimization »
Quoc V. Le · Marc'Aurelio Ranzato · Russ Salakhutdinov · Josh Tenenbaum · Andrew Y Ng -
2011 Poster: Learning to Learn with Compound HD Models »
Russ Salakhutdinov · Josh Tenenbaum · Antonio Torralba -
2011 Spotlight: Learning to Learn with Compound HD Models »
Russ Salakhutdinov · Josh Tenenbaum · Antonio Torralba -
2010 Workshop: Transfer Learning Via Rich Generative Models. »
Russ Salakhutdinov · Ryan Adams · Josh Tenenbaum · Zoubin Ghahramani · Tom Griffiths -
2010 Poster: Dynamic Infinite Relational Model for Time-varying Relational Data Analysis »
Katsuhiko Ishiguro · Tomoharu Iwata · Naonori Ueda · Josh Tenenbaum -
2010 Poster: Nonparametric Bayesian Policy Priors for Reinforcement Learning »
Finale P Doshi-Velez · David Wingate · Nicholas Roy · Josh Tenenbaum -
2009 Workshop: Bounded-rational analyses of human cognition: Bayesian models, approximate inference, and the brain »
Noah Goodman · Edward Vul · Tom Griffiths · Josh Tenenbaum -
2009 Workshop: Analyzing Networks and Learning With Graphs »
Edo M Airoldi · Jure Leskovec · Jon Kleinberg · Josh Tenenbaum -
2009 Poster: Perceptual Multistability as Markov Chain Monte Carlo Inference »
Samuel J Gershman · Edward Vul · Josh Tenenbaum -
2009 Poster: Help or Hinder: Bayesian Models of Social Goal Inference »
Tomer D Ullman · Chris L Baker · Owen Macindoe · Owain Evans · Noah Goodman · Josh Tenenbaum -
2009 Spotlight: Perceptual Multistability as Markov Chain Monte Carlo Inference »
Samuel J Gershman · Edward Vul · Josh Tenenbaum -
2009 Poster: Explaining human multiple object tracking as resource-constrained approximate inference in a dynamic probabilistic model »
Edward Vul · Michael C Frank · George Alvarez · Josh Tenenbaum -
2009 Oral: Explaining human multiple object tracking as resource-constrained approximate inference in a dynamic probabilistic model »
Edward Vul · Michael C Frank · George Alvarez · Josh Tenenbaum -
2009 Poster: Modelling Relational Data using Bayesian Clustered Tensor Factorization »
Ilya Sutskever · Russ Salakhutdinov · Josh Tenenbaum -
2008 Workshop: Probabilistic Programming: Universal Languages, Systems and Applications »
Daniel Roy · John Winn · David A McAllester · Vikash Mansinghka · Josh Tenenbaum -
2008 Workshop: Machine learning meets human learning »
Nathaniel D Daw · Tom Griffiths · Josh Tenenbaum · Jerry Zhu -
2007 Workshop: The Grammar of Vision: Probabilistic Grammar-Based Models for Visual Scene Understanding and Object Categorization »
Virginia Savova · Josh Tenenbaum · Leslie Kaelbling · Alan L Yuille -
2007 Spotlight: A Bayesian Framework for Cross-Situational Word-Learning »
Michael C Frank · Noah Goodman · Josh Tenenbaum -
2007 Poster: A Bayesian Framework for Cross-Situational Word-Learning »
Michael C Frank · Noah Goodman · Josh Tenenbaum -
2007 Poster: A complexity measure for intuitive theories »
Charles Kemp · Noah Goodman · Josh Tenenbaum -
2006 Poster: Combining causal and similarity-based reasoning »
Charles Kemp · Patrick Shafto · Allison Berke · Josh Tenenbaum -
2006 Poster: Multiple timescales and uncertainty in motor adaptation »
Konrad P Kording · Josh Tenenbaum · Reza Shadmehr -
2006 Poster: Learning annotated hierarchies from relational data »
Daniel Roy · Charles Kemp · Vikash Mansinghka · Josh Tenenbaum -
2006 Talk: Learning annotated hierarchies from relational data »
Daniel Roy · Charles Kemp · Vikash Mansinghka · Josh Tenenbaum -
2006 Spotlight: Multiple timescales and uncertainty in motor adaptation »
Konrad P Kording · Josh Tenenbaum · Reza Shadmehr -
2006 Talk: Combining causal and similarity-based reasoning »
Charles Kemp · Patrick Shafto · Allison Berke · Josh Tenenbaum -
2006 Poster: Causal inference in sensorimotor integration »
Konrad P Kording · Josh Tenenbaum -
2006 Tutorial: Bayesian Models of Human Learning and Inference »
Josh Tenenbaum