Hasso-Plattner-Institut
Prof. Dr. Tobias Friedrich
  
 

Competitive Programming with Deep Learning 2

MSc Project Seminar - Winter 2021/22

Personen: Prof. Dr. Tobias Friedrich, Dr. Sarel Cohen, Vanja Doskoč
Links: Lehrveranstaltungen IT-Systems Engineering, Algorithm Engineering Moodle*

*) Should you not have access to the moodle, please contact Vanja Doskoč.

Overview

In this course we will participate in AI (online) competitions using, for example, the Kaggle platform. Please note that this course will be held fully online. Please keep in mind that there is a participants limitation for this course.

Description

In this course, participants (in teams) enter various AI competitions. Thereby, we offer two variations of competitions for the students to participate in: Kaggle competitions or research-oriented competitions. In the former, you participate in a few Kaggle online competitions together with thousands of AI programmers world-wide. The Kaggle competitions will be a good chance for you to practice known deep learning algorithms (as well as other ML techniques) and learn new ones. For the research-oriented competitions, you will elaborate possible (novel) solutions to existing problems, battling with existing state-of-the-art papers.

In both settings, you are free to use any programming language, any libraries, any framework (Pytorch, Keras, Tensorflow, fast.ai, whatever you prefer) and any algorithms (ML or deep learning or even heuristics) as you like. The goal in these competitions will be to maximize your points in the competition.

During the competition, we will assist and guide you (and your team) with weekly meetings, were we discuss possible approaches and the best course of action. There will also be a written part (a short scientific report) where you and your team write about your findings for a selected competition.

Requirements

There are no formal requirements, however, participants are expected to know the basics of deep learning as there will be no teaching part.

Please be aware that this course is taught in English.

Grading

The evaluation of the event is based on the performances of the ongoing contests as well as a short scientific report. The grade is composed as follows:

  • 30% report
  • 70% performance in the contests

Dates

We meet online weekly on ??, at ?? - ??. The technical details for these meetings will be shared via moodle.