Unsupervised Learning by Program Synthesis

Part of Advances in Neural Information Processing Systems 28 (NIPS 2015)

Authors

Kevin Ellis, Armando Solar-Lezama, Josh Tenenbaum

Abstract

We introduce an unsupervised learning algorithmthat combines probabilistic modeling with solver-based techniques for program synthesis.We apply our techniques to both a visual learning domain and a language learning problem,showing that our algorithm can learn many visual concepts from only a few examplesand that it can recover some English inflectional morphology.Taken together, these results give both a new approach to unsupervised learning of symbolic compositional structures,and a technique for applying program synthesis tools to noisy data.