A cross-associative neural network for SVD of non-squared data matrix in signal processing

Author

Feng, Da-Zheng ; Bao, Zheng ; Zhang, Xian-Da

Author_Institution

Lab. of Radar Signal Process., Xidian Univ., Xi´´an, China

Volume

12

Issue

5

fYear

2001

fDate

9/1/2001 12:00:00 AM

Firstpage

1215

Lastpage

1221

Abstract

This paper proposes a cross-associative neural network (CANN) for singular value decomposition (SVD) of a non-squared data matrix in signal processing, in order to improve the convergence speed and avoid the potential instability of the deterministic networks associated with the cross-correlation neural-network models. We study the global asymptotic stability of the network for tracking all the singular components, and show that the selection of its learning rate in the iterative algorithm is independent of the singular value distribution of a non-squared matrix. The performances of CANN are shown via simulations

Keywords

asymptotic stability; convergence of numerical methods; iterative methods; learning (artificial intelligence); neural nets; signal processing; singular value decomposition; asymptotic stability; convergence; cross-associative neural network; iterative method; learning rate; nonsquared data matrix; signal processing; singular value decomposition; Convergence; Data mining; Intelligent networks; Matrices; Matrix decomposition; Neural networks; Sampling methods; Signal processing; Signal processing algorithms; Singular value decomposition;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.950149

Filename

950149