pith. sign in

arxiv: 1706.09751 · v1 · pith:YUA5TFMPnew · submitted 2017-06-29 · 📊 stat.ML

Bayesian Semisupervised Learning with Deep Generative Models

classification 📊 stat.ML
keywords discriminativebayesiancomponentlearningmodelstochasticflexibilitygenerative
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.