Stochastic Continuous-Depth Neural Networks
Forskningsprojekt , 2020 –

we advance the understanding of deep neural networks through the investigation of stochastic continuous-depth neural networks. These can be thought of as deep neural networks (DNN) composed of infinitely many stochastic layers, where each single layer only brings about a gradual change to the output of the preceding layers. We will analyse such stochastic continuous-depth neural networks using tools from stochastic calculus and Bayesian statistics. From that, we will derive practically relevant and novel training algorithms for stochastic DNNs with the aim to capture the uncertainty associated with the predictions of the network. This project is supported by Chalmers AI Research Centre (CHAIR) including Oskar Eklund's PhD position.

Deltagare

Moritz Schauer (kontakt)

Universitetslektor vid Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Oskar Eklund

Doktorand vid Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Annika Lang

Biträdande professor vid Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Finansiering

Chalmers AI-forskningscentrum (CHAIR)

Finansierar Chalmers deltagande under 2020–

Relaterade styrkeområden och infrastruktur

Grundläggande vetenskaper

Fundament

Mer information

Senast uppdaterat

2020-11-27