Coder Social home page Coder Social logo

neurocore-public's Introduction

NeuroCore

We train a simplified NeuroSAT architecture to directly predict the unsatisfiable cores of real problems, and modify MiniSat to periodically replace its variable activity scores with NeuroSAT's prediction of how likely they are to appear in an unsatisfiable core. Our modified MiniSat solves 10% more problems on SAT-COMP 2018 than the original does. Although MiniSat is no longer considered a state-of-the-art solver, our results nonetheless demonstrate the potential for NeuroSAT (and in particular, NeuroCore) to provide useful guidance to CDCL solvers on real problems.

More information can be found in the paper https://arxiv.org/abs/1903.04671.

Overview of repository

  1. solver/: pybind11 module wrapping Z3, for generating training data.
  2. python/gen_data.py: ray script to generate training data.
  3. python/neurosat.py: simplified reimplementation of NeuroSAT.
  4. python/train.py: distributed tensorflow script to train NeuroCore.
  5. hybrids/glucose/: code to extend glucose with NeuroCore.
  6. python/evaluate_cdcl.py: ray script for evaluating solvers on benchmarks.
  7. weights/: the trained weights used for the experiments in the paper.

Dependencies

There are several dependencies. For now, we list the ones that cannot be easily installed with apt-get or pip3:

  1. z3 (we used commit 773c61369480b6f031eb8fa98a7eb24bd52c7070)
  2. drat-trim
  3. eigen
  4. pybind11
  5. minisat
  6. grpc

The code also uses a MariaDB database and an Azure storage account. Replace the fake credentials in auth.json.

Team

neurocore-public's People

Contributors

dselsam avatar

Stargazers

SichaoY avatar Tci Gravifer Fang avatar  avatar  avatar  avatar zhao qianwen avatar ai4verification avatar Xingyu Zhao avatar Qianyi Liu avatar Lee Man avatar Hongce Zhang avatar breandan avatar cheng zhang avatar Joan Espasa avatar Chris Lin avatar yxliang avatar Altan Haan avatar togatoga avatar Eric S. Rogstad avatar Yimeng avatar Bai Yiwei avatar  avatar Anderson avatar  avatar jiawei avatar Xuechen Li avatar Pedro Orvalho avatar  avatar Jakub Błaszczyk avatar AdriBena avatar Nikolay Dubina avatar Zihan Zheng avatar Joe Scott avatar  avatar Nham Le avatar Sumanth Dathathri avatar Saeed Nejati avatar Dimitri Bohlender avatar Junyan Xu avatar

Watchers

James Cloos avatar cheng zhang avatar Eric S. Rogstad avatar yxliang avatar  avatar Joe Scott avatar paper2code - bot avatar

neurocore-public's Issues

interact with solvers

Can you advise how to interact with the solvers to replace the EVSIDS score with the probability produced by neuroCore model?

gen_data.py assumes that sql table exist, no code to create them?

It looks like python/gen_data.py is assuming that a number of tables exist in the SQL database - events, gd_runs and there is no code to create them, and one is left trying to guess what the schema for those tables is supposed to be and then creating them manually.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.