Hierarchical Bayesian models of human inductive learning

Josh Tenenbaum
Massachusetts Institute of Technology
Brain and Cog Sc, CS, and AI

I will show how some of the technical themes introduced in the last two days -- hierarchical Bayesian models, nonparametric Bayes, and Bayesian semi-supervised learning -- can be used to build models of core aspects of human inductive learning, including word learning and property induction.


Presentation (PowerPoint File)

Back to Graduate Summer School: Probabilistic Models of Cognition: The Mathematics of Mind