Skip to content

wgapl/adaptive-neural-compilation

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Adaptive Neural Compilation

This repository contains the code associated to the Adaptive Neural Compilation paper that can be found on arxiv.

In this repository, you can find two projects:

  • The compiler in the compilation/ folder allows to transform a program written in a low level language (examples can be found here) into a set of weights for our model. These weights are represented as a configuration file that will be used by the adaptation project.
  • The learning part in the adaptation/ folder provides the execution model, the training script and all the utilities to run the experiments. Examples of configurations files can be found here and examples of training commands can be found here

If you use this work, please cite:

@article{anc,
    title={Adaptive Neural Compilation},
    author={Bunel, Rudy and Desmaison, Alban and Kohli, Pushmeet and Torr, Philip H.S and Kumar, M. Pawan},
    journal={arXiv preprint arXiv:1605.07969},
    year={2016}
}

Releases

No releases published

Packages

No packages published

Languages

  • Lua 90.7%
  • Haskell 3.6%
  • NewLisp 1.6%
  • Shell 1.4%
  • Yacc 1.0%
  • Makefile 1.0%
  • Other 0.7%