CUED Publications database

Bayesian Semisupervised Learning with Deep Generative Models

Gordon, J and Hernández-Lobato, JM Bayesian Semisupervised Learning with Deep Generative Models. (Unpublished)

Full text not available from this repository.


Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model uncertainty in the estimation of the model's discriminative component and b) lack flexibility to capture complex stochastic patterns in the label generation process. To avoid these problems, we first propose to use a discriminative component with stochastic inputs for increased noise flexibility. We show how an efficient Gibbs sampling procedure can marginalize the stochastic inputs when inferring missing labels in this model. Following this, we extend the discriminative component to be fully Bayesian and produce estimates of uncertainty in its parameter values. This opens the door for semi-supervised Bayesian active learning.

Item Type: Article
Uncontrolled Keywords: stat.ML stat.ML
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:07
Last Modified: 18 Aug 2020 12:35