VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Numerical Analysis Seminar: Deep Neural Network Methods for PDEs
Last Updated: 2026-02-05 16:22:14
Abstract
The seminar will review recent _mathematical results_on approximation power of deep neural networks (DNNs).The focus will be on mathematical proof techniques toobtain approximation rate estimates (in terms of neural networksize and connectivity) on various classes of input dataincluding, in particular, selected types of PDE solutions.
Content
Deep Neural Networks (DNNs) have recently attracted substantial interest and attention due to outperforming the best established techniques in a number of tasks (Chess, Go, Shogi, autonomous driving, language translation, image classification, etc.). In big data analysis, DNNs achieved remarkable performance in computer vision, speech recognition and natural language processing. In many cases, these successes have been achieved by heuristic implementations combined with massive compute power and training data. For a (bird's eye) view, see https://doi.org/10.1017/9781108860604 and, more mathematical and closer to the seminar theme, https://doi.org/10.1109/TIT.2021.3062161 The seminar will review recent _mathematical results_ on approximation power of deep neural networks (DNNs). The focus will be on mathematical proof techniques to obtain approximation rate estimates (in terms of neural network size and connectivity) on various classes of input data including, in particular, selected types of PDE solutions. Mathematical results support that DNNs can equalize or outperform the best mathematical results known to date. Particular cases comprise: high-dimensional parametric maps, analytic and holomorphic maps, maps containing multi-scale features which arise as solution classes from PDEs, classes of maps which are invariant under group actions. Format of the Seminar: The seminar format will be oral student presentations, combined with written report. Student presentations will be based on a recent research paper selected in two meetings at the start of the semester. Grading of the Seminar: Passing grade will require a) 1hr oral presentation _via Zoom_ with Q/A from the seminar group, in early May 2022 and b) typed seminar report (``Ausarbeitung'') of several key aspects of the paper under review. Each seminar topic will allow expansion to a semester or a master thesis in the MSc MATH or MSc Applied MATH. Disclaimer: The seminar will _not_ address recent developments in DNN software, eg. TENSORFLOW, and algorithmic training heuristics, or programming techniques for DNN training in various specific applications.
General Information
- Language
- English
- Levels
- MSC
- Frequency
- Yearly recurring
Examination
- Type
- ungraded semester performance
Registration & Places
- Signup Start
- 02.01.2023
- Signup End
- 17.02.2023
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| seminar |
Numerical Analysis Seminar: Deep Neural Network Methods for PDEs
Permission from lecturers required for all students.
|
|
2 h weekly |
Offered In
-
-
-
Seminars (NOTICE: The number of seminar places is limited, and the special selection procedure should help to allocate the places not primarily according to the registration time. For the seminars with pecial selection procedure everybody is waitlisted first when he/she tries to register for a seminar in myStudies. Moreover: At most 2 mathematics seminars can be chosen per semester. In case you need to attend 3 seminars in this semester, please take contact with the Study Administration (email: ).)
-
-