Welling , Max and Weber, Markus (2001) A Constrained EM Algorithm for Independent Component Analysis. Neural Computation, 13 (3). pp. 677-689. ISSN 0899-7667. http://resolver.caltech.edu/CaltechAUTHORS:20111109-084139616
- Published Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20111109-084139616
We introduce a novel way of performing independent component analysis using a constrained version of the expectation-maximization (EM) algorithm. The source distributions are modeled as D one-dimensional mixtures of gaussians. The observed data are modeled as linear mixtures of the sources with additive, isotropic noise. This generative model is fit to the data using constrained EM. The simpler “soft-switching” approach is introduced, which uses only one parameter to decide on the sub- or supergaussian nature of the sources. We explain how our approach relates to independent factor analysis.
|Additional Information:||© 2001 Massachusetts Institute of Technology. Received March 15, 1999; accepted June 1, 2000. Posted Online March 13, 2006. We thank Pietro Perona for stimulating discussions and the referees for many suggestions that improved the text significantly. M. Welling acknowledges the Sloan Center for its ongoing financial support.|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||18 Jan 2012 22:15|
|Last Modified:||26 Dec 2012 14:23|
Repository Staff Only: item control page