Holophrasm: a neural Automated Theorem Prover for higher-order logic

8 Aug 2016  ·  Daniel Whalen ·

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.

PDF Abstract


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Automated Theorem Proving Metamath set.mm Holophrasm Percentage correct 14.3 # 3


No methods listed for this paper. Add relevant methods here