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:
|Sep 24||Introduction to the seminar (topics, objectives, structure):||Dr. Veselin Raychev|
|15.10||Parameter-Free Probabilistic API Mining across GitHub||Anastasia Sycheva||Inna Grijnevitch|
|Code Completion with Neural Attention and Pointer Networks||Ylli Muhadri||Jingxuan He|
|22.10||Learn&Fuzz: Machine Learning for Input Fuzzing||Nicolas Mesot||Pesho Ivanov|
|An Encoder-Decoder Framework Translating Natural Language to Database Queries||Ming-Da Liu Zhang||Pavol Bielik|
|29.10||Predicting Program Properties from "Big Code"||Panayiotis Panayiotou||Dana Drachsler Cohen|
|05.11||RobustFill: Neural Program Learning under Noisy I/O||Momchil Pavlinov Peychev||Benjamin Bichsel|
|DeepBugs: A Learning Approach to Name-based Bug Detection||Pietro Constante Oldrati||Samuel Steffen|