Prof. Joshua Brett Tenenbaum

Professor of Cognitive Science and Computation

Primary DLC

Department of Brain and Cognitive Sciences

MIT Room: 46-4015

Areas of Interest and Expertise

Computational Models of Similarity, Categorization and Concepts
Structure Discovery in Unsupervised Learning and Perceptual Organization
Machine Learning

Research Summary

Tenenbaum’s research currently focuses on two areas: describing the structure, content, and development of people’s commonsense theories, especially intuitive physics and intuitive psychology, and understanding how people are able to learn and generalize new concepts, models, theories and tasks from very few examples -- often called "one-shot learning.” Through a combination of mathematical modeling, computer simulation and behavioral experiments, his team works 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.

Recent Work