English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Using kernel PCA for Initialisation of Variational Bayesian Nonlinear Blind Source Separation Method

Honkela, A., Harmeling, S., Lundqvist, L., & Valpola, H. (2004). Using kernel PCA for Initialisation of Variational Bayesian Nonlinear Blind Source Separation Method. Independent Component Analysis and Blind Signal Separation: Fifth International Conference (ICA 2004), 790-797.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Honkela, A, Author
Harmeling, S1, Author           
Lundqvist, L, Author
Valpola, H, Author
Puntonet A. Prieto, C. G., Editor
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              

Content

show
hide
Free keywords: -
 Abstract: The variational Bayesian nonlinear blind source separation method introduced by Lappalainen and Honkela in 2000 is initialised with linear principal component analysis (PCA). Because of the multilayer perceptron (MLP) network used to model the nonlinearity, the method is susceptible to local minima and therefore sensitive to the initialisation used. As the method is used for nonlinear separation, the linear initialisation may in some cases lead it astray. In this paper we study the use of kernel PCA (KPCA) in the initialisation. KPCA is a rather straightforward generalisation of linear PCA and it is much faster to compute than the variational Bayesian method. The experiments show that it can produce significantly better initialisations than linear PCA. Additionally, the model comparison methods provided by the variational Bayesian framework can be easily applied to compare different kernels.

Details

show
hide
Language(s):
 Dates: 2004-10
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/b100528
BibTex Citekey: 6353
 Degree: -

Event

show
hide
Title: Fifth International Conference on Independent Component Analysis and Blind Signal Separation
Place of Event: Granada, Spain
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Independent Component Analysis and Blind Signal Separation: Fifth International Conference (ICA 2004)
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 790 - 797 Identifier: -