Startseite UB

A Geometric Algorithm for Overcomplete Linear ICA

Theis, Fabian J. and Lang, Elmar and Puntonet, Carlos G. (2004) A Geometric Algorithm for Overcomplete Linear ICA. Neurocomputing 56, pp. 381-398.

Full text not available from this repository.

at publisher (via DOI)

Other URL: http://homepages.uni-regensburg.de/~thf11669/publications/theis04overcomplete_neurocomp.pdf


Abstract

We generalize geometric algorithms to overcomplete cases with more sources than sensors. With geometric ICA we get an efficient method for the matrix-recovery step in the framework of a two-step approach to the source separation problem. The second step - source-recovery - uses a maximum-likelihood approach. There we prove that the shortest-path algorithm as proposed by Bofill and Zibulevsky ...

plus


Export bibliographical data



Item Type:Article
Date:2004
Institutions:Biology, Preclinical Medicine > Institut für Biophysik und physikalische Biochemie > Prof. Dr. Elmar Lang
Biology, Preclinical Medicine > Institut für Biophysik und physikalische Biochemie > Prof. Dr. Elmar Lang > Arbeitsgruppe Dr. Fabian Theis
Projects:Graduiertenkolleg Nichtlinearität und Nichtgleichgewicht
Identification Number:
ValueType
10.1016/j.neucom.2003.09.008DOI
Subjects:500 Science > 530 Physics
500 Science > 570 Life sciences
Status:Published
Refereed:Yes, this version has been refereed
Created at the University of Regensburg:Yes
Owner: Redakteur Physik
Deposited On:20 Mar 2007
Last Modified:04 Oct 2010 07:47
Item ID:1585
Owner Only: item control page
  1. University

University Library

Publication Server

Contact person
Gernot Deinzer

Telefon 0941 943-2759
Contact