Stability of cellular neural networks with opposite-sign templates

Author

Zou, Fan ; Nossek, Josef A.

Author_Institution

Inst. for Network Theory & Design, Tech. Univ. of Munich, Germany

Volume

38

Issue

6

fYear

1991

fDate

6/1/1991 12:00:00 AM

Firstpage

675

Lastpage

677

Abstract

Cellular neural networks (CNNs) with opposite-sign templates have been successfully applied by T. Matsumoto et al. in connected component detection (CCD) in feature extraction (see ibid., vol.37, p.633-5, 1990). A stability analysis of this class of nonreciprocal CNN is provided by L.O. Chua et al. (see ibid., vol.37, p.1520-7, 1990). In this paper, a thorough stability analysis of this type of CNNs which shows the dependence of complete stability on the template values is presented. Parameter regions for complete stability and instability are determined, and the parameter region for the functionality of CCD is also given based on this investigation. Simulation examples verify that the complete stability of CNN with opposite-sign templates is not always preserved

Keywords

neural nets; pattern recognition; stability; cellular neural networks; connected component detection; feature extraction; opposite-sign templates; parameter region; stability analysis; template values; Cellular neural networks; Charge coupled devices; Control systems; Eigenvalues and eigenfunctions; Equations; Feature extraction; Jacobian matrices; Neural networks; Piecewise linear techniques; Stability analysis;

fLanguage

English

Journal_Title

Circuits and Systems, IEEE Transactions on

Publisher

ieee

ISSN

0098-4094

Type

jour

DOI

10.1109/31.81867

Filename

81867