NeurIPS 2016poster184 citations

DeepMath - Deep Sequence Models for Premise Selection

Geoffrey Irving, Christian Szegedy, Alexander A Alemi, Niklas Een, Francois Chollet, Josef Urban

Abstract

We study the effectiveness of neural sequence models for premise selection in automated theorem proving, a key bottleneck for progress in formalized mathematics. We propose a two stage approach for this task that yields good results for the premise selection task on the Mizar corpus while avoiding the hand-engineered features of existing state-of-the-art models. To our knowledge, this is the first time deep learning has been applied theorem proving on a large scale.

BibTeX
@inproceedings{NIPS2016_f197002b,
 author = {Irving, Geoffrey and Szegedy, Christian and Alemi, Alexander A and Een, Niklas and Chollet, Francois and Urban, Josef},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {D. Lee and M. Sugiyama and U. Luxburg and I. Guyon and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {DeepMath - Deep Sequence Models for Premise Selection},
 url = {https://proceedings.neurips.cc/paper_files/paper/2016/file/f197002b9a0853eca5e046d9ca4663d5-Paper.pdf},
 volume = {29},
 year = {2016}
}