Universität Wien FIND

Get vaccinated to work and study safely together in autumn.

To enable a smooth and safe start into the semester for all members of the University of Vienna, you can get vaccinated without prior appointment on the Campus of the University of Vienna from Saturday, 18 September, until Monday, 20 September. More information: https://www.univie.ac.at/en/about-us/further-information/coronavirus/.

Warning! The directory is not yet complete and will be amended until the beginning of the term.

250106 VO Neural Network Theory (2021W)

3.00 ECTS (2.00 SWS), SPL 25 - Mathematik
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

Language: English

Lecturers

Classes (iCal) - next class is marked with N

Monday 11.10. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 18.10. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 25.10. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 08.11. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 15.11. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 22.11. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 29.11. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 06.12. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 13.12. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 10.01. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 17.01. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 24.01. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock
Monday 31.01. 16:45 - 18:15 Seminarraum 10 Oskar-Morgenstern-Platz 1 2.Stock

Information

Aims, contents and method of the course

Deep neural networks form the backbone of most modern machine learning algorithms. Additionally, neural networks are mathematical objects that can be theoretically analysed to obtain profound insights explaining many phenomena that are observed in applications. In this lecture series, we present a comprehensive collection of such results.

Lecture notes will be supplied.

This class will _not_ discuss algorithms to train deep neural networks for various specific applications.

Assessment and permitted materials

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

Minimum requirements and assessment criteria

The lecture can be followed best with a working knowledge of basic concepts of functional analysis and Fourier analysis.

Examination topics

Everything covered in the course.

Reading list

Peter L. Bartlett, Martin Anthony, Neural Network Learning: Theoretical Foundations, Cambridge University Press,1999

The lecture notes (http://pc-petersen.eu/Neural_Network_Theory.pdf )

Association in the course directory

MAMV; MSTV

Last modified: We 15.09.2021 16:08