Part of Advances in Neural Information Processing Systems 29 (NIPS 2016)
Geoffrey Irving, Christian Szegedy, Alexander A Alemi, Niklas Een, Francois Chollet, Josef Urban
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.