English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Joint Diagonalization of Several Scatter Matrices for ICA

Nordhausen, K., Gutch, H. W., Oja, H., & Theis, F. J. (2012). Joint Diagonalization of Several Scatter Matrices for ICA. In F. J. Theis, A. Cichocki, A. Yeredor, & M. Zibulevsky (Eds.), Latent Variable Analysis and Signal Separation (pp. 172-179). Berlin Heidelberg: Springer Berlin Heidelberg.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Nordhausen, Klaus, Author
Gutch, Harold W.1, Author           
Oja, Hannu, Author
Theis, Fabian J., Author
Affiliations:
1Department of Nonlinear Dynamics, Max Planck Institute for Dynamics and Self-Organization, Max Planck Society, ou_2063286              

Content

show
hide
Free keywords: -
 Abstract: Procedures such as FOBI that jointly diagonalize two matrices with the independence property have a long tradition in ICA. These procedures have well-known statistical properties, for example they are prone to failure if the sources have multiple identical values on the diagonal. In this paper we suggest to diagonalize jointly $k\ge 2$ scatter matrices havingthe independence property. For the joint diagonalization we suggest a novel algorithm which finds the correct direction in an deflation-based manner, one after another. The resulting algorithm can also handle degenerate signals and is robust against noise. This is demonstrated in a simulation study.

Details

show
hide
Language(s): eng - English
 Dates: 2012
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 633608
DOI: 10.1007/978-3-642-28551-6_22
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Latent Variable Analysis and Signal Separation
Source Genre: Book
 Creator(s):
Theis, Fabian J., Editor
Cichocki, Andrzej, Editor
Yeredor, Arie, Editor
Zibulevsky, Michael, Editor
Affiliations:
-
Publ. Info: Berlin Heidelberg : Springer Berlin Heidelberg
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 172 - 179 Identifier: -

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -