Practical Course - Analysis of new phenomena in machine/deep learning (IN2106, IN4317)
Course 0000000825 in SS 2023
General Data
| Course Type | practical training |
|---|---|
| Semester Weekly Hours | 6 SWS |
| Organisational Unit | Informatics 7 - Chair of Theoretical Computer Science (Prof. Esparza) |
| Lecturers |
Pascal Esser Debarghya Ghoshdastidar Satyaki Mukherjee Mahalakshmi Sabanayagam |
| Dates |
2 singular or moved dates |
Assignment to Modules
-
IN2106: Master-Praktikum / Advanced Practical Course
This module is included in the following catalogs:- Further Modules from Other Disciplines
Further Information
Courses are together with exams the building blocks for modules. Please keep in mind that information on the contents, learning outcomes and, especially examination conditions are given on the module level only – see section "Assignment to Modules" above.
| additional remarks | Deep neural networks produce state-of-the-art results on a wide range of machine learning problems. While deep learning still remains elusive to rigorous theoretical analysis, its phenomenal performance has shaken the mathematical foundations of machine learning—contradicting many conventional beliefs of classical learning theory and the fundamental understanding of how algorithms can successfully learn patterns. However, the past few years have seen an exciting combination of mathematical and empirical research, uncovering some of the mysteries of modern machine/deep learning and development of formal theories to explain them, such as: 1. Generalization: Why do classical theories fail to explain generalization in deep networks? 2. Over-parameterization: When overfitting can be good for learning? 3. Kernel behavior: When do neural networks behave identical to kernel methods? 4. Robustness: Why are some neural networks more robust? Why can specific changes in data trick the predictions of neural networks? This course will familiarize the students with empirical practices used to explain surprising phenomena in deep learning. In particular, the students will be asked to reproduce empirical findings of recent papers from top ML conferences (Neurips, ICML, ICLR and AISTATS) and empirically extend these observations to more complex problems/models. |
|---|---|
| Links |
E-Learning course (e. g. Moodle) TUMonline entry |
Equivalent Courses (e. g. in other semesters)
| Semester | Title | Lecturers | Dates |
|---|---|---|---|
| SS 2024 | Practical Course - Analysis of new phenomena in machine/deep learning (IN0012, IN2106, IN4317) | Esser, P. Ghoshdastidar, D. Sabanayagam, M. | |
| SS 2022 | Practical Course - Analysis of new phenomena in machine/deep learning (IN2106, IN4317) | Esser, P. Ghoshdastidar, D. Mukherjee, S. Sabanayagam, M. |
Tue, 10:00–12:00, MI 03.09.014 Tue, 14:00–16:00, MI 03.09.014 Fri, 12:00–14:00, MI 03.09.014 |