Independent component analysis: recent advances

Independent component analysis is a probabilistic method for learning a linear transform of a random vector. The goal is to find components that are maximally independent and non-Gaussian (non-normal). Its fundamental difference to classical multi-variate statistical methods is in the assumption of...

Full description

Saved in:
Bibliographic Details
Published inPhilosophical transactions of the Royal Society of London. Series A: Mathematical, physical, and engineering sciences Vol. 371; no. 1984; p. 20110534
Main Author Hyvärinen, Aapo
Format Journal Article
LanguageEnglish
Published England The Royal Society Publishing 13.02.2013
Subjects
Blind Source Separation
Causal Analysis
Independent Component Analysis
Non-Gaussianity
Review
Online AccessGet full text

Cover

More Information
Summary:Independent component analysis is a probabilistic method for learning a linear transform of a random vector. The goal is to find components that are maximally independent and non-Gaussian (non-normal). Its fundamental difference to classical multi-variate statistical methods is in the assumption of non-Gaussianity, which enables the identification of original, underlying components, in contrast to classical methods. The basic theory of independent component analysis was mainly developed in the 1990s and summarized, for example, in our monograph in 2001. Here, we provide an overview of some recent developments in the theory since the year 2000. The main topics are: analysis of causal relations, testing independent components, analysing multiple datasets (three-way data), modelling dependencies between the components and improved methods for estimating the basic model.
Bibliography:istex:479199FCB8A72590D83ECB0AD2685C5F22D81959
href:rsta20110534.pdf
ark:/67375/V84-8358K2G9-D
ArticleID:rsta20110534
One contribution of 17 to a Discussion Meeting Issue 'Signal processing and inference for the physical sciences'.
Discussion Meeting Issue 'Signal processing and inference for the physical sciences' organized and edited by Nick S. Jones and Thomas J. Maccarone
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
One contribution of 17 to a Discussion Meeting Issue ‘Signal processing and inference for the physical sciences’.
ISSN:1364-503X
1471-2962
DOI:10.1098/rsta.2011.0534