Learning deep sigmoid belief networks with data augmentation

Published

Conference Paper

Copyright 2015 by the authors. Deep directed generative models are developed. The multi-layered model is designed by stacking sigmoid belief networks, with sparsity-encouraging priors placed on the model parameters. Learning and inference of layer-wise model parameters are implemented in a Bayesian setting. By exploring the idea of data augmentation and introducing auxiliary Polya-Gamma variables, simple and efficient Gibbs sampling and mean-field variational Bayes (VB) inference are implemented. To address large-scale datasets, an online version of VB is also developed. Experimental results are presented for three publicly available datasets: MNIST, Caltech 101 Silhouettes and OCR letters.

Duke Authors

Cited Authors

  • Gan, Z; Henao, R; Carlson, D; Carin, L

Published Date

  • January 1, 2015

Published In

Volume / Issue

  • 38 /

Start / End Page

  • 268 - 276

Electronic International Standard Serial Number (EISSN)

  • 1533-7928

International Standard Serial Number (ISSN)

  • 1532-4435

Citation Source

  • Scopus