Independent Component Analysis, a new concept?

Abstract : The independent component analysis (ICA) of a random vector consists of searching for a linear transformation that minimizes the statistical dependence between its components. In order to define suitable search criteria, the expansion of mutual information is utilized as a function of cumulants of increasing orders. An efficient algorithm is proposed, which allows the computation of the ICA of a data matrix within a polynomial time. The concept oflCA may actually be seen as an extension of the principal component analysis (PCA), which can only impose independence up to the second order and, consequently, defines directions that are orthogonal. Potential applications of ICA include data analysis and compression, Bayesian detection, localization of sources, and blind identification and deconvolution.
Type de document :
Article dans une revue
Signal Processing, Elsevier, 1994, 36, pp.287-314. <10.1016/0165-1684(94)90029-9>
Liste complète des métadonnées
Contributeur : Pierre Comon <>
Soumis le : jeudi 26 mars 2015 - 18:16:28
Dernière modification le : mercredi 8 avril 2015 - 16:36:03
Document(s) archivé(s) le : mardi 18 avril 2017 - 00:38:46


como94-SP (1).pdf
Accord explicite pour ce dépôt




Pierre Comon. Independent Component Analysis, a new concept?. Signal Processing, Elsevier, 1994, 36, pp.287-314. <10.1016/0165-1684(94)90029-9>. <hal-00417283>



Consultations de
la notice


Téléchargements du document