Holophrasm: a neural Automated Theorem Prover for higher-order logic
Published in
arXiv.org(2016)External Links:
TL
TL;DR
Holophrasm exploits the formalism of the Metamath language and explores partial proof trees using a neural-network-augmented bandit algorithm and a sequence-to-sequence model for action enumeration.
Abstract
I propose a system for Automated Theorem Proving in higher order logic using deep learning and eschewing hand-constructed features. Holophrasm exploits the formalism of the Metamath language and explores partial proof trees using a neural-network-augmented bandit algorithm and a sequence-to-sequence model for action enumeration. The system proves 14% of its test theorems from Metamath's set.mm module.
References18 items
1
DeepMath - Deep Sequence Models for Premise Selection
2
Mastering the game of Go with deep neural networks and tree search
3
Effective Approaches to Attention-based Neural Machine Translation
4
Adam: A Method for Stochastic Optimization
5