Deep Learning with Hierarchical Convolutional Factor Analysis.

Bo Chen, Gungor Polatkan, Guillermo Sapiro, David M. Blei, David B. Dunson, Lawrence Carin

Abstract

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.
BibTeX
@article{chen2013deep,
  author = {Bo Chen and Gungor Polatkan and Guillermo Sapiro and David M. Blei and David B. Dunson and Lawrence Carin},
  title = {{Deep Learning with Hierarchical Convolutional Factor Analysis.}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2013},
  doi = {10.1109/tpami.2013.19},
}

Loading related content...

Figure