|
|
|
| Status | Confirmed |
| Seminar Series | MATH-IHES |
| Subjects | hep-th |
| Date | Monday 25 November 2019 |
| Time | 15:00 |
| Institute | IHES |
| Seminar Room | Centre de conférences Marilyn et James Simons |
| Speaker's Last Name | Jacquet |
| Speaker's First Name | Philippe |
| Speaker's Email Address | |
| Speaker's Institution | INRIA, Nokia Bell Labs |
| Title | Al vs Information Theory and Learnability |
| Abstract | We will first give a quick review of how information theory impacts AI, in particular how a complex system can evolve into a more complex system while satisfying the laws of information theory. Second we will investigate the problem of learnability. Deep neural networks are sometimes uncapable of learning surprisingly simple problems, we will try to hint a characterization of those problems. |
| arXiv Preprint Number | |
| Comments | Nokia-IHES Workshop |
| Attachments |
To Generate a poster for this seminar : [ Postscript | PDF ]
|
|
[ English version ] |