|
|
|
| Statut | Confirmé |
| Série | MATH-IHES |
| Domaines | hep-th |
| Date | Lundi 25 Novembre 2019 |
| Heure | 15:00 |
| Institut | IHES |
| Salle | Centre de conférences Marilyn et James Simons |
| Nom de l'orateur | Jacquet |
| Prenom de l'orateur | Philippe |
| Addresse email de l'orateur | |
| Institution de l'orateur | INRIA, Nokia Bell Labs |
| Titre | Al vs Information Theory and Learnability |
| Résumé | 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. |
| Numéro de preprint arXiv | |
| Commentaires | Nokia-IHES Workshop |
| Fichiers attachés |
Pour obtenir l' affiche de ce séminaire : [ Postscript | PDF ]
|
|
[ English version ] |