227-0423-00L Neural Network Theory
| Semester | Herbstsemester 2022 |
| Dozierende | H. Bölcskei |
| Periodizität | jährlich wiederkehrende Veranstaltung |
| Lehrveranstaltung | Findet dieses Semester nicht statt. |
| Lehrsprache | Englisch |
| Kurzbeschreibung | The class focuses on fundamental mathematical aspects of neural networks with an emphasis on deep networks: Universal approximation theorems, capacity of separating surfaces, generalization, fundamental limits of deep neural network learning, VC dimension. |
| Lernziel | After attending this lecture, participating in the exercise sessions, and working on the homework problem sets, students will have acquired a working knowledge of the mathematical foundations of neural networks. |
| Inhalt | 1. Universal approximation with single- and multi-layer networks 2. Introduction to approximation theory: Fundamental limits on compressibility of signal classes, Kolmogorov epsilon-entropy of signal classes, non-linear approximation theory 3. Fundamental limits of deep neural network learning 4. Geometry of decision surfaces 5. Separating capacity of nonlinear decision surfaces 6. Vapnik-Chervonenkis (VC) dimension 7. VC dimension of neural networks 8. Generalization error in neural network learning |
| Skript | Detailed lecture notes are available on the course web page https://www.mins.ee.ethz.ch/teaching/nnt/ |
| Voraussetzungen / Besonderes | This course is aimed at students with a strong mathematical background in general, and in linear algebra, analysis, and probability theory in particular. |