The objective of the seminar is to:
- Introduce students to the 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:
|Introduction to the seminar (topics, objectives, structure):||Martin Vechev|
|March 12||DeepCoder: Learning to Write Programs||Patrick Schmidt||Veselin Raychev|
|A Bimodal Modelling of Source Code and Natural Language||Sandro Marcon||Pesho Ivanov|
|March 19||Detecting object usage anomalies||Flavia Cavallaro||Benjamin Bichsel|
|sk_p: a neural program corrector for MOOCs||Andrea Rinaldi||Pavol Bielik|
|March 26||Probabilistic Model for Code with Decision Trees||Robin Vaaler||Timon Gehr|
|April 9||Code Completion with Neural Attention and Pointer Networks||Ondrej Skopek||Pavol Bielik|
|Learning to Represent Programs with Graphs||Mislav Balunovic||Benjamin Bichsel|
|April 23||Melford: Using Neural Networks to Find Spreadsheet Errors||Hlynur Freyr||Pesho Ivanov|
|A Convolutional Attention Network for Extreme Summarization of Source Code||Jovan Andonov||Veselin Raychev|