Unsupervised Learning by Program Synthesis

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.

Cite

Text

Ellis et al. "Unsupervised Learning by Program Synthesis." Neural Information Processing Systems, 2015.

Markdown

[Ellis et al. "Unsupervised Learning by Program Synthesis." Neural Information Processing Systems, 2015.](https://mlanthology.org/neurips/2015/ellis2015neurips-unsupervised/)

BibTeX

@inproceedings{ellis2015neurips-unsupervised,
  title     = {{Unsupervised Learning by Program Synthesis}},
  author    = {Ellis, Kevin and Solar-Lezama, Armando and Tenenbaum, Josh},
  booktitle = {Neural Information Processing Systems},
  year      = {2015},
  pages     = {973-981},
  url       = {https://mlanthology.org/neurips/2015/ellis2015neurips-unsupervised/}
}