Deep learning with differential Gaussian process flows

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Researchers

Research units

Abstract

We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks

Details

Original languageEnglish
Title of host publicationThe 22nd International Conference on Artificial Intelligence and Statistic
Publication statusPublished - Apr 2019
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Artificial Intelligence and Statistics - Naha, Japan
Duration: 16 Apr 201918 Apr 2019
Conference number: 22

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume89
ISSN (Electronic)2640-3498

Conference

ConferenceInternational Conference on Artificial Intelligence and Statistics
Abbreviated titleAISTATS
CountryJapan
CityNaha
Period16/04/201918/04/2019

    Research areas

  • gaussian process, Bayesian methods

ID: 36413733