https://github.com/tensorflow/deepmath

Experiments towards neural network theorem proving
https://github.com/tensorflow/deepmath

Last synced: about 1 month ago
JSON representation

Experiments towards neural network theorem proving

• Host: GitHub
• URL: https://github.com/tensorflow/deepmath
• Owner: tensorflow
• License: apache-2.0
• Archived: true
• Created: 2016-11-07T21:31:44.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2020-12-05T10:44:01.000Z (almost 4 years ago)
• Last Synced: 2024-09-23T07:32:46.508Z (about 1 month ago)
• Language: C++
• Size: 3.32 MB
• Stars: 785
• Watchers: 65
• Forks: 137
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-bazel - DeepMath

README

        
# Deepmath

The Deepmath project seeks to improve automated theorem proving using deep

learning and other machine learning techniques.  Deepmath is a collaboration

between [Google Research](https://research.google.com) and several universities.

## DISCLAIMER:

The source code in this repository is not an official Google product, but

is a research collaboration with external research teams.

## Installation

Deepmath depends on TensorFlow, which is included as a submodule.  Use, or

see, the Dockerfile for build instructions for `deephol`, our neural prover. It

requires connecting to a proof assistant server. See

https://github.com/brain-research/hol-light for a server implementation.