Course Introduction

In this course, we will learn

• What machine learning for SE is
• What you can do with it
• How to do it

We will also learn

• How to read papers critically (this lecture!)
• How to discuss papers
• How to write SE papers
• How to do ML4SE in practice

Course Teachers

• Georgios Gousios
• Maurício Aniche
• Diomidis Spinellis

How will we study

The course is a seminar / project based. Therefore:

• We will study papers, lots of them!
• We will write nice summaries
• We will present the results of our study in the classroom
• We will work in groups (3-4 people)
• We will develop ML methods for SE problems

How to get a paper

• At Uni!

• Via VPN (to Uni). TU Delft has contracts with most major Tech publishers to get you free access to papers.

Q How much does one article cost?

• There are alternatives …

We use Google Scholar to retrieve metrics. There is other tools such as Scopus. Even the IEEE Xplore Digital Library gives metrics.

Course deliverable: ML solution 4 SE problem

To finish this course:

• Select one of those research topics
• Use ML (however advanced or naive) to solve it. No heuristics allowed!
• Present your solution in front of a panel of judges
  • Also, create and present your poster during industry/academia event
• Win swag by FaceBook, Microsoft or SourceD!

Grading

• Deliverable grade (80%):

  • Peer grading: The final papers will be peer-reviewed by 2-3 teams.
  • Teachers will not give any grades.

• Final presentation grade:

  • Panel grading (20%): An expert panel (under construction) will give students grades during their final presentations

Deadlines

• Selection of topic: Fri 6th Sep
• First version of pipeline: Mon, 30th Sep
• Report + solution: Fri 25th Oct
• Peer-review: Wed 30th Oct
• Presentation + Poster: Fri 1st Nov

TODO for today

• Form a group
• Study the course materials and select a topic
• Register your group and prefered topics. Use this form: XXX

Lecture notes

• Freely available on the web, on Georgios’s homepage (http://gousios.gr/courses/ml4se/)

• You can print/download them before the lecture and bring them along to make additional notes.

• We are looking forward to improve them! If you have suggestions, find mistakes etc, let us know!

Bibliography

Copyright

The course contents are copyrighted (c) 2018 - onwards by TU Delft and their respective authors and licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license.