Learning Naïve Physics Models by Analogical Generalization

S. Friedman, J. Taylor, K. Forbus

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

How do people learn intuitive models of the world from experience? We describe a simulation that uses analogical generalization to learn naïve models of pushing and blocking from experience. Experiences are represented by a type of comic strip, consisting of sequences of sketches and simplified English that are automatically encoded by the simulation. We show that the models it learns are compatible with naïve models found in the literature, and analyze the effects of presentation order.
Original languageEnglish
Title of host publicationProceedings of the 2nd International Analogy Conference
StatePublished - 2009
EventProceedings of the 2nd International Analogy Conference - Sofia, Bulgaria
Duration: Jul 1 2009 → …

Conference

ConferenceProceedings of the 2nd International Analogy Conference
Period7/1/09 → …

Fingerprint Dive into the research topics of 'Learning Naïve Physics Models by Analogical Generalization'. Together they form a unique fingerprint.

Cite this