Mathematical Introduction to Deep Neural Networks

Professor: JProf. Dr. Diyora Salimova
E-Mail Professor: diyora.salimova@mathematik.uni-freiburg.de
Lecture: Wedndesday 12-14, SR 226, Hermann-Herder-Str. 10
Office Hours: by arrangement, R 208, Hermann-Herder-Str. 10
Exercises: Monday 16-18, SR 226, Hermann-Herder-Str. 10
Assistant: M.Sc. Ilkhom Mukhammadiev
E-Mail Assistant: ilkhom.mukhammadiev@mathematik.uni-freiburg.de
Office Hours: by arrangement, R 210, Hermann-Herder-Str. 10

Content

The course will provide an introduction to deep learning algorithms with a focus on the mathematical understanding of the objects and methods used. Essential components of deep learning algorithms will be reviewed, including different neural network architectures and optimization algorithms. The course will cover theoretical aspects of deep learning algorithms, including their approximation capabilities, optimization theory, and error analysis.

Studien-/Prüfungsleistungen

Studienleistung: Achieving 50 % of exercise points.

Prüfungsleistung: Completion of the Studienleistung and successful participation in the exam.

Lecture Notes

The lecture notes will be uploaded online: Lecture notes

Exercise Groups

Exercise groups begin during the second week of lectures and take place weekly.
TimeRoomTutorSubmission
Monday 16-18 SR 226 (Hermann-Herder-Str. 10) Ilkhom Wednesday, 14:00

Exercise Sheets

The exercise sheets consist of exercises from the script (see below). Submission at the letterbox @@@ next to CIP-Pool (Hermann-Herder-Str. 10) or via e-mail until Wednesday 14:00. The exercise sheets can be submitted in groups of two. In that case equal contribution from both of the students is expected.

 Sheet Exercises Deadline
1 @@@ @@@@
2 @@@ @@@@