💻 Codelab

Machine Learning on Source Code (MLonCode) is an emerging and exciting research domain which stands at the sweet spot between deep learning, natural language processing, social science, and programming.

During this 2 hours workshop, we are going to show you how to extract insights from code bases—step by step—by shedding light on those crucial aspects:

  • What information is available in your code
  • How to extract this information
  • What can you do with this knowledge: what are the tasks solvable by MLonCode
  • Which models can be used to solve them

To get our hands dirty, we will solve several example tasks, using source{d}, an open source stack to gain insights from codebases:

  • Suggest function names automatically
  • Cluster developers
  • Search projects by similarity

Prerequisites: a laptop with Docker installed. We will provide an image to all participants.