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
Feb 18	Introduction to the seminar (topics, objectives, structure):	Dr. Veselin Raychev
Mar 04	Bugs as Deviant Behavior: A General Approach to Inferring Errors in Systems Code	Rubin Deliallisi	Pavol
Mar 11	Parameter-Free Probabilistic API Mining across GitHub	Bernhard Kellermann	Timon
	Tracelet-Based Code Search in Executables	Stewart Webb	Marc
Mar 18	Compilation Error Repair: For the Student Programs, From the Student Programs	Benjamin Schmid	Mislav
	Synthesizing Programs for Images using Reinforced Adversarial Learning	Zacharias Fisches	Matthew
Mar 25	RobustFill: Neural Program Learning under Noisy I/O	Svilen Stefanov	Timon
	Dynamic Neural Program Embeddings for Program Repair	Roman Haag	Marc
Apr 01	Learning Loop Invariants for Program Verification	Tierry Hörmann	Mislav
	Selecting Representative Examples for Program Synthesis	Christian Bräm	Pavol
Apr 15	Tree-to-tree Neural Networks for Program Translation	Mounir Amrani	Pavol
	Estimating Types in Binaries using Predictive Modeling	Yuanhao Huang	Veselin
Apr 29	Neural Guided Constraint Logic Programming for Program Synthesis	David Yenicelik	Matthew
	PHOG: Probabilistic Model for Code	Sven Knobloch	Marc
May 6	Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection	Hrishikesh Gupta	Veselin