EE Distinguished Speakers Seminar: Geometric perspectives on deep learning models
Event details
| Date | 12.05.2020 |
| Hour | 14:00 › 15:00 |
| Speaker | Pascal Frossard has been a faculty at EPFL since 2003, and he leads the Signal Processing Laboratory (LTS4) of the Electrical Engineering Institute. His research interests include network data analysis, image representation and understanding, signal processing and machine learning. Before joining EPFL, he was a member of the research staff at the IBM T. J. Watson Research Center, Yorktown Heights, NY, USA. |
| Location |
Zoom
|
| Category | Conferences - Seminars |
Abstract: Learning-based decision systems become state-of-the-art in numerous application domains. In particular, deep learning has developed as a standard in vision and speech applications for example. Despite this success, important research questions remain open: the robustness of deep learning systems is surprisingly low, and the interpretation of their decisions is often challenging. We will overview the recent research developed at the LTS4 laboratory, towards developing algorithms for measuring the robustness of deep networks, deriving geometric insights on their behaviour, and designing more effective systems.
Zoom link: https://epfl.zoom.us/j/96097462787?pwd=MUE1R0NxODVQNUFSZ0lqdlA4RWF5UT09
Zoom link: https://epfl.zoom.us/j/96097462787?pwd=MUE1R0NxODVQNUFSZ0lqdlA4RWF5UT09
Links
Practical information
- General public
- Free
Organizer
- EE Institute
Contact
- Prof. Pascal Frossard - +41 21 693 56 55 - [email protected]