- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- BIRS Workshop Lecture Videos /
- Bayesian GANs and Stochastic MCMC
Open Collections
BIRS Workshop Lecture Videos
BIRS Workshop Lecture Videos
Bayesian GANs and Stochastic MCMC Wilson, Andrew
Description
Through an adversarial game, generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. I will present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. Within this framework, we use stochastic gradient Hamiltonian Monte Carlo for marginalizing parameters. The resulting approach can automatically discover complementary and interpretable generative hypotheses for collections of images. Moreover, by exploring an expressive posterior over these hypotheses, we show that it is possible to achieve state-of-the-art quantitative results on image classification benchmarks, even with less than 1% of the labelled training data.
Item Metadata
Title |
Bayesian GANs and Stochastic MCMC
|
Creator | |
Publisher |
Banff International Research Station for Mathematical Innovation and Discovery
|
Date Issued |
2018-01-17T10:01
|
Description |
Through an adversarial game, generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. I will present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. Within this framework, we use stochastic gradient Hamiltonian Monte Carlo for marginalizing parameters. The resulting approach can automatically discover complementary and interpretable generative hypotheses for collections of images. Moreover, by exploring an expressive posterior over these hypotheses, we show that it is possible to achieve state-of-the-art quantitative results on image classification benchmarks, even with less than 1% of the labelled training data.
|
Extent |
50 minutes
|
Subject | |
Type | |
File Format |
video/mp4
|
Language |
eng
|
Notes |
Author affiliation: Cornell University
|
Series | |
Date Available |
2018-07-17
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
DOI |
10.14288/1.0368958
|
URI | |
Affiliation | |
Peer Review Status |
Unreviewed
|
Scholarly Level |
Faculty
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International