Many real world concepts, such as “car”, “house”, and “tree”,are more than simply a collection of features. These objectsare richly structured, defined in terms of systems of relations,subparts, and recursive embeddings. We describe an approachto concept representation and learning that attempts to capturesuch structured objects. This approach builds on recent proba-bilistic approaches, viewing concepts as generative processes,and on recent rule-based approaches, constructing concepts in-ductively from a language of thought. Concepts are modeledas probabilistic programs that describe generative processes;these programs are described in a compositional language. Inan exploratory concept learning experiment, we investigate hu-man learning from sets of tree-like objects generated by pro-cesses that vary in their abstract structure, from simple proto-types to complex recursions. We compare human categoriza-tion judgements to predictions of the true generative process aswell as a variety of exemplar-based heuristics.
展开▼