| RUS ENG |
| Полная версия |
|
|
|
| СЕМИНАРЫ |
|
Совместный общематематический семинар СПбГУ и Пекинского Университета
|
|||
|
|
|||
|
Exploring Stochastic Methods For Deep Learning and Reinforcement Learning Zaiwen Wen Beijing International Center for Mathematical Research |
|||
|
Аннотация: Stochastic methods are widely used in machine learning. In this talk, we present a structured stochastic quasi-Newton method and a sketchy empirical natural gradient method for deep learning. We also introduce a stochastic quadratic penalty algorithm for reinforcement learning. Язык доклада: английский |
|||