Deep Learning with Hierarchical Convolutional Factor Analysis.

Journal Article (Journal Article)

Unsupervised multi-layered ("deep") models are considered for general data, with a particular focus on 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. In order to address large-scale and streaming data, an online version of VB is also developed. The number of basis functions or 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.

Duke Authors

Cited Authors

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

Published Date

  • January 2013

Published In

PubMed ID

  • 23319498

Electronic International Standard Serial Number (EISSN)

  • 1939-3539

International Standard Serial Number (ISSN)

  • 0162-8828


  • eng