Machine Learning on src

Applying machine learning and deep learning representations on source code for various problems

Description

Applying machine learning and deep learning representations on source code for various problems. This area is connected to Big Code as many times it involves mining large software repositories. The related bliki page contains a sections discussing papers and resources around the area.

Projects

Codrep 2019 competitions

We got the 2nd place in the CodRep 2019 competition, organized by KTH. Our approach is summarized in this gist.

Tools

gh-downloader

gh-downloader is a useful tool for downloding GitHub repositories in archive format for further processing.

Diploma Theses

I've worked on the subject with diploma theses students in the following proejcts: