Universität Wien FIND

Return to Vienna for the summer semester of 2022. We are planning to hold courses mainly on site to enable the personal exchange between you, your teachers and fellow students. We have labelled digital and mixed courses in u:find accordingly.

Due to COVID-19, there might be changes at short notice (e.g. individual classes in a digital format). Obtain information about the current status on u:find and check your e-mails regularly.

Please read the information on https://studieren.univie.ac.at/en/info.

053630 SE Research Seminar (2021W)

Deep Learning

Continuous assessment of course work
MIXED

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 25 participants
Language: English

Lecturers

Classes (iCal) - next class is marked with N

If possible, talks will be given on site. We will try to provide live streams via Moodle but would like to encourage everyone to join the sessions in person as often as possible.

Monday 04.10. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 11.10. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 18.10. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 25.10. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 08.11. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 15.11. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 22.11. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 29.11. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 06.12. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 13.12. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 10.01. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 17.01. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 24.01. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00
Monday 31.01. 09:45 - 11:15 Seminarraum 5, Kolingasse 14-16, EG00

Information

Aims, contents and method of the course

We will discuss the foundations and some of the most prominent applications of deep learning. Advanced topics will include selected mathematical aspects of deep learning and topics from the emerging research field of scientifc machine learning.

Assessment and permitted materials

Live presentation, written paper, participation in the seminar.

Minimum requirements and assessment criteria

The final grade will be based on the presentation in the seminar (40 %), the written paper (40 %) and participation during the seminnar (20 %). Passing grades on the presentation and the written paper, and a participation rate of at least 80 % are mandatory for an overall passing grade.

Examination topics

Reading list

A list of topics and the respective literature will be made available via Moodle and discussed during the first session of the seminar (4.10). (edited)

Association in the course directory

Last modified: Mo 21.02.2022 13:08