course: Master Project DSP

number:
142040
teaching methods:
project
media:
Videoübertragung, overhead transparencies, Moodle
responsible person:
Prof. Dr.-Ing. Do­ro­thea Kolossa
Lecturers:
Prof. Dr.-Ing. Do­ro­thea Kolossa (ETIT), M. Sc. Wentao Yu (ETIT)
language:
german
HWS:
3
CP:
see examination rules
offered in:
summer term

dates in summer term

  • kick-off meeting: Friday the 16.04.2021 from 10:00 to 11.00 o'clock

Exam

Die Angaben zu den Prüfungsmodalitäten (im WiSe 2020/2021 | SoSe 2021) erfolgen vorbehaltlich der aktuellen Situation. Notwendige Änderungen aufgrund universitärer Vorgaben werden zeitnah bekanntgegeben.
Form of exam:project
Registration for exam:None
continual assessment

goals

In addition to strategies and methods for the solution of technical challenges, the students learn the organization of large projects in teams, methods of project planning, and structured software development including specification and unit testing.

content

Due to the currently implemented emergency regulations at the RUB for the summer term 2021, this project will be offered as an online class. Therefore, all meetings are carried out with the help of video conferences. The details will be presented in the first online meeting on April 16, 2021, 10-11 am. Any questions in this respect will be answered in this meeting.

Registration for the course in advance is mandatory!

Please send an email until April 14, 2021, 11:59 p.m. using your RUB email address with the subject "An­mel­dung Kurs 142040 SoSe2021" to wentao.yu[at]rub.de and benedikt.boenninghoff[at]rub.de. All further information will be sent to the participants by email on April 15, 2021.

In this year, students will develop a larger data science project in teams of 2 to 10 students. The aim is to develop and test a machine learning framework for multimodal author profiling. Python is selected as the programming language for this project.

In the course of the semester, the lab is supported in the form of a weekly online meeting, in which participation is mandatory. To pass the lab, we expect a deployed and executable submission of the best-performing solution via GitHub, a final report (Latex) which documents the code and its performance, and a final presentation via an online meeting tool.

requirements

keine

recommended knowledge

  • Basic knowledge of digital signal processing and machine learning
  • good programming skills
  • ideally, experience in Python programming