Deep learning with hierarchical convolutional factor analysis.

Published

Journal Article

Unsupervised multilayered (“deep”) models are considered for imagery. The model is represented using a hierarchical convolutional factor-analysis construction, with sparse factor loadings and scores. The computation of layer-dependent model parameters is implemented within a Bayesian setting, employing a Gibbs sampler and variational Bayesian (VB) analysis that explicitly exploit the convolutional nature of the expansion. To address large-scale and streaming data, an online version of VB is also developed. The number of dictionary elements at each layer is inferred from the data, based on a beta-Bernoulli implementation of the Indian buffet process. Example results are presented for several image-processing applications, with comparisons to related models in the literature.

Full Text

Duke Authors

Cited Authors

  • Chen, B; Polatkan, G; Sapiro, G; Blei, D; Dunson, D; Carin, L

Published Date

  • August 2013

Published In

Volume / Issue

  • 35 / 8

Start / End Page

  • 1887 - 1901

PubMed ID

  • 23787342

Pubmed Central ID

  • 23787342

Electronic International Standard Serial Number (EISSN)

  • 1939-3539

International Standard Serial Number (ISSN)

  • 0162-8828

Digital Object Identifier (DOI)

  • 10.1109/tpami.2013.19

Language

  • eng