UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Bruno: A deep recurrent model for exchangeable data

Korshunova, I; Degrave, J; Huszár, F; Gal, Y; Gretton, A; Dambre, J; (2018) Bruno: A deep recurrent model for exchangeable data. In: Advances in Neural Information Processing Systems 31 (NIPS 2018). (pp. pp. 7190-7198). Neural Information Processing Systems Foundation, Inc.: Montréal, Canada. Green open access

[thumbnail of 7949-bruno-a-deep-recurrent-model-for-exchangeable-data.pdf]
Preview
Text
7949-bruno-a-deep-recurrent-model-for-exchangeable-data.pdf - Published Version

Download (343kB) | Preview

Abstract

We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations. Our model is provably exchangeable, meaning that the joint distribution over observations is invariant under permutation: this property lies at the heart of Bayesian inference. The model does not require variational approximations to train, and new samples can be generated conditional on previous samples, with cost linear in the size of the conditioning set. The advantages of our architecture are demonstrated on learning tasks that require generalisation from short observed sequences while modelling sequence variability, such as conditional image generation, few-shot learning, and anomaly detection

Type: Proceedings paper
Title: Bruno: A deep recurrent model for exchangeable data
Event: 32nd International Conference on Neural Information Processing Systems
Location: Montréal, Canada
Dates: 2-8th December 2018
Open access status: An open access version is available from UCL Discovery
Publisher version: https://papers.nips.cc/paper/7949-bruno-a-deep-rec...
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit
URI: https://discovery.ucl.ac.uk/id/eprint/10076519
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item