Journée de Rham 2017 : Mathematical Mysteries of Deep Networks
Event details
Date | 08.03.2017 |
Hour | 15:30 › 16:30 |
Speaker | Stéphane Mallat, Ecole Normale Supérieure, Paris |
Location | |
Category | Conferences - Seminars |
Deep convolutional networks provide state of the art classifications and regressions results over many high-dimensional problems including image, audio and bio-medical signal recognition, with spectacular results. They are able to approximate high-dimensional functionals without suffering from the curse of dimensionality. We shall review their architecture and concentrate on the analysis of their mathematical properties, which are mostly not understood. Applications will be shown for image and audio processing, but also to approximate complex stochastic processes for statistical physics, and quantum chemistry.
Practical information
- General public
- Free
Organizer
- Prof. Clément Hongler et Prof. Marc Troyanov
Contact
- Marie Munoz