Skip to contentSkip to filters

We use cookies for analytics.

Pre-language learning of conceptual structures

Cognition, Artificial Intelligence and seminar by Shimon Ullman, Weizmann Institute of Science

Hosted by Simons Institute for the Theory of Computing

Thursday 09:30 Los Angeles (GMT-7)

Recording available

Berkeley, United States
Related content

Recording

42 min

Abstract

Infants develop concepts and relations before acquiring substantial language, often with little explicit supervision. This talk presents computational models of that early learning and compares them with language-centred AI training. It asks whether the conceptual structures formed before language could provide useful ingredients for artificial learning systems.

Topics

early learningcomputational modelsconceptual structuresartificial learning systemslanguage-centred AI