Joshua Tenenbaum

Co-Scientific Director, MIT Quest for Intelligence; Professor, Brain and Cognitive Sciences; MacArthur Fellow

Joshua Tenenbaum is a professor of computational cognitive science in MIT’s Department of Brain and Cognitive Sciences and a scientific director with the MIT Quest for Intelligence. He is also an investigator at the Center for Brains, Minds and Machines and the Computer Science and Artificial Intelligence Laboratory. Tenenbaum’s research straddles cognitive science and artificial intelligence, where his goals are to reverse engineer human intelligence and to build machines that behave in human-like ways and have greater use to society. Through a combination of mathematical modeling, computer simulation, and behavioral experiments, Tenenbaum tries to uncover the logic behind our everyday inductive leaps: constructing perceptual representations, separating “style” and “content” in perception, learning concepts and words, judging similarity or representativeness, inferring causal connections, noticing coincidences and predicting the future. Tenenbaum is a MacArthur Fellow and has received the National Academy of Sciences’ Troland Research Award. He earned a BA from Yale University, and a PhD in brain and cognitive sciences from MIT.

Publications

Media

Videos

 

Top Work

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

Neuro-Symbolic AI

Publications with the MIT-IBM Watson AI Lab

Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks
Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks
 
GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling
GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling
 
Learning Symbolic Operators for Task and Motion Planning
Learning Symbolic Operators for Task and Motion Planning
 
Few-Shot Bayesian Imitation Learning with Logical Program Policies
Few-Shot Bayesian Imitation Learning with Logical Program Policies
 
Temporal and Object Quantification Networks
Temporal and Object Quantification Networks
 
Discovering State and Action Abstractions for Generalized Task and Motion Planning
Discovering State and Action Abstractions for Generalized Task and Motion Planning
 
A large-scale benchmark for few-shot program induction and synthesis
A large-scale benchmark for few-shot program induction and synthesis
 
STAR: A Benchmark for Situated Reasoning in Real-World Videos
STAR: A Benchmark for Situated Reasoning in Real-World Videos
 
ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation
ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation
 
3DP3: 3D Scene Perception via Probabilistic Programming
3DP3: 3D Scene Perception via Probabilistic Programming
 
A Bayesian Symbolic Approach to Reasoning and Learning in Intuitive Physics
A Bayesian Symbolic Approach to Reasoning and Learning in Intuitive Physics
 
Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language
Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language
 
PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
 
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
 
Learning Physical Graph Representations from Visual Scenes
Learning Physical Graph Representations from Visual Scenes
 
Online Bayesian Goal Inference for Boundedly-Rational Planning Agents
Online Bayesian Goal Inference for Boundedly-Rational Planning Agents
 
CLEVRER: The first video dataset for neuro-symbolic reasoning
CLEVRER: The first video dataset for neuro-symbolic reasoning
 
Deep Audio Priors Emerge From Harmonic Convolutional Networks
Deep Audio Priors Emerge From Harmonic Convolutional Networks
 
ObjectNet: A bias-controlled dataset object recognition
ObjectNet: A bias-controlled dataset object recognition
 
Visual Concept-Metaconcept Learning
Visual Concept-Metaconcept Learning
 
Write, Execute, Assess: Program Synthesis with a REPL
Write, Execute, Assess: Program Synthesis with a REPL
 
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
 
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
 
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding