Cross-correlation neural network models

Author

Diamantaras, Konstantinos I. ; Kung, Sun-Yuan

Author_Institution

Siemens Corp. Res. Inc., Princeton, NJ, USA

Volume

42

Issue

11

fYear

1994

fDate

11/1/1994 12:00:00 AM

Firstpage

3218

Lastpage

3223

Abstract

In this paper we provide theoretical foundations for a new neural model for singular value decomposition based on an extension of the Hebbian learning rule called the cross-coupled Hebbian rule. The model is extracting the SVD of the cross-correlation matrix of two stochastic signals and is an extension on previous work on neural-network-related principal component analysis (PCA). We prove the asymptotic convergence of the network to the principal (normalized) singular vectors of the cross-correlation and we provide simulation results which suggest that the convergence is exponential. The new model may have useful applications in the problems of filtering for signal processing and signal detection

Keywords

Hebbian learning; correlation methods; filtering theory; multilayer perceptrons; signal detection; signal processing; singular value decomposition; statistical analysis; Hebbian learning rule; PCA; SVD; cross-correlation; cross-correlation matrix; cross-coupled Hebbian rule; exponential convergence; filtering; neural network models; principal component analysis; signal detection; signal processing; simulation results; singular value decomposition; stochastic signals; symptotic convergence; Convergence; Filtering; Hebbian theory; Matrix decomposition; Neural networks; Principal component analysis; Signal detection; Signal processing; Singular value decomposition; Stochastic processes;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.330379

Filename

330379