DeepMath - Deep Sequence Models for Premise Selection

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.

Authors

• Geoffrey Irving
• Christian Szegedy
• Alexander Alemi
• Niklas Een
• Francois Chollet
• Josef Urban Czech Technical University in Prague

Keywords

No keywords are indexed for this paper.