Learning Naïve Physics Models by Analogical Generalization
Suzanne Friedman, Jason Taylor, Kenneth D. Forbus · 2009
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.