Generating and generalizing models of visual objects

摘要

We report on initial experiments with an implemented learning system whose inputs are images of two-dimensional shapes. The system first builds semantic network descriptions of shapes based on Brady's “smoothed local symmetry” representation. It learns shape models from them using a substantially modified version of Winston's analogy program. A generalization of Gray coding enables the representation to be extended and also allows a single operation, called “ablation,” to achieve the effects of many standard induction heuristics. The program can learn disjunctions, and can learn concepts using only positive examples. We discuss learnability and the pervasive importance of representational hierarchies.