Deep Learning for Big Code

Overview

The objective of the seminar is to:

Introduce students to the emerging field of Deep Learning for Big Code.
Learn how machine learning models can be used to solve practical challenges in software engineering and programming beyond traditional methods.
Highlight the latest research and work opportunities in industry and academia available on this topic.

The seminar is carried out as a set of presentations (2 each lecture) chosen from a set of available papers (available below). The grade is determined as a function of the presentation, handling questions and answers, and participation:

Schedule

Date	Title	Presenter	Advisor
17.02	Introduction to the seminar (topics, objectives, structure):	Pavol Bielik
02.03	Mining Version Histories to Guide Software Changes	Martin Villavicencio	Mathhew Mirman
	Code Completion with Neural Attention and Pointer Networks	Anton Lu	Momchil Peychev
09.03	Compilation Error Repair: For the Student Programs, From the Student Programs	Valentino Föhn	Timon Gehr
	Learning a Static Analyzer from Data	Kevin De Keyser	Jingxuan He
16.03	Dynamic Neural Program Embeddings for Program Repair	Felix Huber	Veselin Raychev
	Hoppity: Learning Bug Detection and Repair	Allain Ryser	Pavol Bielik
23.03	Synthesizing Datalog Programs Using Numerical Relaxation	Filip Meier	Rudiger Birkner
	Locate-Then-Detect: Real-time Web Attack Detection via Attention-based Deep Neural Networks	Daniel Stekol	Jingxuan He
30.03	Selecting Representative Examples for Program Synthesis	Nikola Jovanović	Veselin Raychev
	SPoC: Search-based Pseudocode to Code	Dominik Häner	Timon Gehr
06.04	Programmatically Interpretable Reinforcement Learning	Jakub Kotal	Momchil Peychev