course: Master-Seminar Deep Learning

number:
141214
teaching methods:
seminar
responsible person:
Prof. Dr.-Ing. Aydin Sezgin
Lecturers:
Prof. Dr.-Ing. Aydin Sezgin (ETIT), M. Sc. Alaa Alameer (ETIT)
language:
german
HWS:
3
CP:
3
offered in:

Exam

All statements pertaining to examination modalities (for the summer/winter term of 2020) are given with reservations. Changes due to new requirements from the university will be announced as soon as possible.
Form of exam:seminar
Registration for exam:Directly with the lecturer
continual assessment

goals

The students will learn how to deal with technical and scientific literature and the presentation of scientific results.

content

The focus of this seminar is on the applications and algorithms of deep-learning in the area of information and communication theory.

Each student should provide a presentation in English about a specific topic chosen from a scientific paper in this domain. Beside the presentation each student must submit a report of around 20 pages (in English or in German) explaining the studied problem and the techniques used to solve it. In all presentations there will be a discussion between the presenter and the audience.

requirements

keine

recommended knowledge

basics of signal and system theory, communication techniques, optimization and probability theory.

miscellaneous

Since a sufficient number of topics have be prepared in advance based on the number of participants in this course, we ask all the interested students to register at the digital communication secretary office ID 2/347 by latest one week before the first meeting in this course. Regarding the writeup, there will be a latex-template (e.g., IEEE­tran mit DIN A4, two column format) and the limit of the number of pages (one column format) should not exceed 20. Regarding the presentation: the time is limited to 20 minutes, at the end of the presentation there will be discussions and questions which could last 5 to 10 minutes. It is recommended that the presentations are prepared for general audiences (the content in the slides, the presentation style ...etc) so the audience can follow.