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

Flexible and accurate inference and learning for deep generative models

Vertes, E; Sahani, M; (2018) Flexible and accurate inference and learning for deep generative models. In: Proceedings of 32nd Conference on Neural Information Processing Systems (NeurIPS 2018),. Neural Information Processing Systems (NIPS): Montréal, Canada.. Green open access

[thumbnail of vertes-sahani-2018-nips-pre.pdf]
Preview
Text
vertes-sahani-2018-nips-pre.pdf - Accepted Version

Download (1MB) | Preview

Abstract

We introduce a new approach to learning in hierarchical latent-variable generative models called the "distributed distributional code Helmholtz machine", which emphasises flexibility and accuracy in the inferential process. In common with the original Helmholtz machine and later variational autoencoder algorithms (but unlike adverserial methods) our approach learns an explicit inference or "recognition" model to approximate the posterior distribution over the latent variables. Unlike in these earlier methods, the posterior representation is not limited to a narrow tractable parameterised form (nor is it represented by samples). To train the generative and recognition models we develop an extended wake-sleep algorithm inspired by the original Helmholtz Machine. This makes it possible to learn hierarchical latent models with both discrete and continuous variables, where an accurate posterior representation is essential. We demonstrate that the new algorithm outperforms current state-of-the-art methods on synthetic, natural image patch and the MNIST data sets.

Type: Proceedings paper
Title: Flexible and accurate inference and learning for deep generative models
Event: 32nd Conference on Neural Information Processing Systems (NeurIPS 2018),
Open access status: An open access version is available from UCL Discovery
Publisher version: https://papers.nips.cc/paper/7671-flexible-and-acc...
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
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/10063532
Downloads since deposit
45Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item