DocumentCode
1009625
Title
Investigations on non-Gaussian factor analysis
Author
Liu, Zhi-Yong ; Chiu, Kai-Chun ; Xu, Lei
Author_Institution
Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, China
Volume
11
Issue
7
fYear
2004
fDate
7/1/2004 12:00:00 AM
Firstpage
597
Lastpage
600
Abstract
This letter further explores the Bayesian Ying-Yang learning based non-Gaussian factor analysis (NFA) via investigating its key yet analytically intractable factor estimating step. Among the three suggested numerical approaches we empirically show that the so-called iterative fixed posteriori approximation approach is the most optimal, as well as theoretically prove that the iterative fixed posteriori approximation is another type of EM-algorithm, with the proof of its convergence also shown.
Keywords
Bayes methods; convergence of numerical methods; independent component analysis; iterative methods; learning (artificial intelligence); signal processing; Bayesian Ying-Yang learning; EM-algorithm; NFA; independent component analysis; iterative fixed posteriori approximation; nonGaussian factor analysis; Additive noise; Algorithm design and analysis; Bayesian methods; Convergence of numerical methods; Gaussian noise; Helium; Independent component analysis; Iterative algorithms; Iterative methods; Signal processing algorithms;
fLanguage
English
Journal_Title
Signal Processing Letters, IEEE
Publisher
ieee
ISSN
1070-9908
Type
jour
DOI
10.1109/LSP.2004.828928
Filename
1306472
Link To Document