A Spurious Equilibria-free Learning Algorithm for the BlindSeparation of Non-zoer Skewness Signals

Authors:
Seungjin Choi;Ruey-Wen Liu;Andrzej Cichocki
Affiliations:
School of Electrical and Electronics Engineering, Chungbunk National University, 48 Kaeshin-Dong, Cheongju, Chungbuk 361–763, Korea;Department of Electrical Engineering, University of Notre Dame, Notre Dame, IN 46556, USA;Lab for Open Information Systems, Brain Science Institute, RIKEN, 2–1 Hirosawa, Wako-shi, Saitama 351–1, Japan E-mail: schoi@engine.chungbuk.ac.kr
Venue:
Neural Processing Letters
Year:
1998

Citing 2
Cited 2

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Equivariant adaptive source separation

IEEE Transactions on Signal Processing

Flexible Independent Component Analysis

Journal of VLSI Signal Processing Systems
Independent arrays or independent time courses for gene expression time series data analysis

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a new learning algorithm for the blind separation ofindependent source signals having non-zero skewness (the 3rd-order cumulant)(the source signals have non-symmetric probability distribution.), fromtheir linear mixtures. It is shown that for a class of source signals whoseprobability distribution functions is not symmetric, a simple adaptivelearning algorithm using quadratic function (f(x)=x^2) is veryefficient for blind source separation task. It is proved that all stableequilibria of the proposed learning algorithm are desirable solutions.Extensive computer simulation experiments confirmed the validity of theproposed algorithm.