Skip to main content

Deep Learning with Hierarchical Convolutional Factor Analysis

Author(s): Chen, Bo; Polatkan, Gungor; Sapiro, Guillermo; Blei, David M.; Dunson, David; et al

To refer to this page use:
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.
Publication Date: Aug-2013
Citation: Chen, Bo, Gungor Polatkan, Guillermo Sapiro, David Blei, David Dunson, and Lawrence Carin. "Deep learning with hierarchical convolutional factor analysis." IEEE transactions on pattern analysis and machine intelligence 35, no. 8 (2013): 1887-1901. doi:10.1109/TPAMI.2013.19
DOI: 10.1109/TPAMI.2013.19
ISSN: 0162-8828
EISSN: 1939-3539
Pages: 1887 - 1901
Type of Material: Journal Article
Journal/Proceeding Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.