Banner Spotlight on Research

Spotlight on Research with Moritz Schauer

​Recurrent stochastic continuous depth networks
Photo of Moritz Schauer
Stochastic continuous depth networks are mathematical models for analyzing the behavior of residual neural networks when many stochastic network layers are stacked. In the limit of many layers of infinitesimal changes they can be described by a stochastic differential equation. Such continuous-depth networks share the expressiveness of deep neural networks and can be trained efficiently through back-propagation. In the talk I discuss recurrent stochastic continuous depth networks for input and output data in time domain.

The work is related to the Stochastic Continuous-Depth Neural Networks project, supported by CHAIR.

Moritz Schauer is an Associate Senior Lecturer at the Department of Mathematical Sciences.

Category Seminar
Location: Online, register to receive the link
Starts: 10 June, 2022, 14:00
Ends: 10 June, 2022, 15:00

Page manager Published: Wed 25 May 2022.