Jim Davies and Ashok K. Goel
College of Computing
Georgia Institute of Technology, Atlanta
jim@jimdavies.org, goel@cc.gatech.edu
in Proceedings of the International Joint Conference on
Artificial Intelligence 2001.
Computational models of analogical problem solving have traditionally described source and target domains in terms of their causal structure. But psychological research shows that visual reasoning plays a part for many kinds of analogies. This paper describes a model that transfers a solution from a source analog to a new target problem using only visual knowledge represented symbolically. The knowledge representation is based on a language of primitive visual elements and transformations. We found that visual knowledge is sufficient for transfer, but that causal knowledge is needed to determine if the transferred solution is appropriate.