Universität Wien

053611 VU Mathematics of Data Science (2025W)

4.00 ECTS (3.00 SWS), SPL 5 - Informatik und Wirtschaftsinformatik
Continuous assessment of course work
Moodle
Tu 09.12. 08:00-11:15 Seminarraum 18 Kolingasse 14-16, OG02

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

Lectures always start at 9:00 AM.

  • Tuesday 07.10. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 14.10. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 21.10. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 28.10. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 04.11. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 11.11. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 18.11. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 25.11. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 02.12. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 16.12. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 13.01. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 20.01. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02
  • Tuesday 27.01. 08:00 - 11:15 Seminarraum 18 Kolingasse 14-16, OG02

Information

Aims, contents and method of the course

This course establishes a mathematical basis required to understand tools and methods in data science. Since it is expected that the students in this course come from a broad range of academic backgrounds, the classes will be adapted to the prior knowledge of the students.

In this course we will get to know the following topics in various degrees of depth: statistics, high-dimensionality and dimension reduction, principle components analysis, graphs and clustering, recommender systems, universal function approximators, statistical learning theory, deep neural networks, future computing paradigms.

Assessment and permitted materials

There will be an oral exam at the end of the semester.

Minimum requirements and assessment criteria

Basic knowledge of all mathematical concepts presented in the lecture.

Examination topics

Everything covered in the lectures.

Reading list

I provide lecture notes. In addition, there are
- Bishop: Pattern Recognition and Machine Learning
- Bandeira, Singer, Strohmer: Mathematics of Data Science, https://people.math.ethz.ch/~abandeira/BandeiraSingerStrohmer-MDS-draft.pdf
- Petersen, Zech: Mathematical theory of deep learning, https://arxiv.org/abs/2407.18384

Association in the course directory

Modul: MDS

Last modified: Tu 21.10.2025 13:25