Variational Bayesian learning of sparse representations and its application in functional neuroimaging

Published

Journal Article

Recent theoretical and experimental work in imaging neuroscience reveals that activations inferred from functional MRI data have sparse structure. We view sparse representation as a problem in Bayesian inference, following a machine learning approach, and construct a structured generative latent-variable model employing adaptive sparsity-inducing priors. The construction allows for automatic complexity control and regularization as well as denoising. Experimental results with benchmark datasets show that the proposed algorithm outperforms standard tools for model-free decompositions such as independent component analysis. © 2012 Springer-Verlag.

Full Text

Duke Authors

Cited Authors

  • Roussos, E; Roberts, S; Daubechies, I

Published Date

  • November 30, 2012

Published In

Volume / Issue

  • 7263 LNAI /

Start / End Page

  • 218 - 225

Electronic International Standard Serial Number (EISSN)

  • 1611-3349

International Standard Serial Number (ISSN)

  • 0302-9743

Digital Object Identifier (DOI)

  • 10.1007/978-3-642-34713-9_28

Citation Source

  • Scopus