Department of Mathematics
 Search | Help | Login | pdf version | printable version

Math @ Duke



Publications [#264871] of Guillermo Sapiro

Papers Published

  1. Chen, B; Polatkan, G; Sapiro, G; Blei, D; Dunson, D; Carin, L, Deep Learning with Hierarchical Convolutional Factor Analysis., IEEE Transactions on Pattern Analysis and Machine Intelligence (January, 2013) [23319498]
    (last updated on 2017/12/13)

    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.
ph: 919.660.2800
fax: 919.660.2821

Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320