Universität Wien

250074 VO Deep Learning (2019S)

5.00 ECTS (3.00 SWS), SPL 25 - Mathematik
Moodle

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).
Register/Deregister for this course

Details

Language: English

Examination dates

Lecturers

Classes (iCal) - next class is marked with N

  • Monday 04.03. 11:30 - 12:15 Seminarraum 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 06.03. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 11.03. 11:30 - 12:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
    Seminarraum 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 13.03. 11:30 - 13:00 Hörsaal 17 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 18.03. 11:30 - 12:15 Hörsaal 17 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 20.03. 11:30 - 13:00 Hörsaal 17 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 25.03. 11:30 - 12:15 Seminarraum 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 27.03. 11:30 - 13:00 Seminarraum 7 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 01.04. 11:30 - 12:15 Seminarraum 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 03.04. 11:30 - 13:00 Seminarraum 7 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 08.04. 11:30 - 12:15 Seminarraum 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 10.04. 11:30 - 13:00 Seminarraum 7 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 29.04. 11:30 - 12:15 Hörsaal 10 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 06.05. 11:30 - 12:15 Hörsaal 12 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 08.05. 11:30 - 13:00 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
  • Monday 13.05. 11:30 - 12:15 Hörsaal 10 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 15.05. 11:30 - 13:00 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
  • Monday 20.05. 11:30 - 12:15 Hörsaal 10 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 22.05. 11:30 - 13:00 Seminarraum 7 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 27.05. 11:30 - 12:15 Hörsaal 12 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 29.05. 11:30 - 13:00 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
  • Monday 03.06. 11:30 - 12:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 05.06. 11:30 - 13:00 Hörsaal 15 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 12.06. 11:30 - 13:00 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
  • Monday 17.06. 11:30 - 12:15 Hörsaal 5 Oskar-Morgenstern-Platz 1 Erdgeschoß
  • Wednesday 19.06. 11:30 - 13:00 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
  • Monday 24.06. 11:30 - 12:15 Hörsaal 15 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 26.06. 11:30 - 13:00 Hörsaal 12 Oskar-Morgenstern-Platz 1 2.Stock

Information

Aims, contents and method of the course

Deep Learning has become the state of the art method for a large number of tasks in artificial intelligence. These methods have achieved (super) human performance on a number of problems and have a tremendous impact on many aspects of our society.
Deep Learning has become the state of the art method for a large number of tasks in artificial intelligence. These methods have achieved (super) human performance on a number of problems and have a tremendous impact on many aspects of our society.

This course will enable the students to understand and use deep learning methods.

We will focus on mathematical understanding but also cover implementation aspects using Keras and GPU computing.

Tentative Syllabus:

1. Foundations of Statistical Learning Theory
2. Classical ML Models
3. Neural Networks
4. Expressivity of Neural Networks
5. Breaking the Curse of Dimensionality with Deep Learning

Assessment and permitted materials

Oral Exam

Minimum requirements and assessment criteria

Examination topics

Reading list

I. Goodfellow, Y. Bengio and A. Courville. Deep Learning. (2016). Available from http://www.deeplearningbook.org.

L Devroye, L Györfi, G Lugosi. A Probabilistic Theory of Pattern Recognition (2013). Springer.

F. Chollet. Deep Learning with Python (2017). Manning.

P. Grohs, D. Perekrestenko, D. Elbrächter, H. Bölcskei. Deep Neural Network Approximation Theory. Available from https://arxiv.org/abs/1901.02220

J. Berner, P. Grohs, A. Jentzen. Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations. Available from https://arxiv.org/abs/1809.03062.

Association in the course directory

MAMV

Last modified: Th 25.02.2021 00:23