MISEP-an ICA method for linear and nonlinear mixtures, based on mutual information

Author

Almeida, Luís B.

Author_Institution

Instituto Superior Tecnico, Lisbon, Portugal

Volume

1

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

442

Lastpage

447

Abstract

Presents MISEP, an independent components analysis method for linear and nonlinear mixtures. The method is based on the minimization of the mutual information of the estimated components, and can be seen as an extension of the well known INFOMAX method in two aspects: (1) allowing the analysis of nonlinear mixtures, and (2) automatically estimating the optimal nonlinearities to be used at the outputs during learning. The resulting ICA method consists of the training of a single specialized multilayer perceptron, optimized according to a single objective function: the output entropy. Some examples of the application of the method are given

Keywords

entropy; learning (artificial intelligence); maximum likelihood estimation; minimisation; multilayer perceptrons; statistics; ICA method; MISEP; learning; linear mixtures; minimization; mutual information; nonlinear mixtures; optimal nonlinearities; specialized multilayer perceptron; Density measurement; Ear; Entropy; Independent component analysis; Information analysis; Multidimensional systems; Multilayer perceptrons; Mutual information; Optimization methods; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1005513

Filename

1005513