Cooperative and competitive cellular neural networks

Author

Mori, Masashi ; Tanji, Yuichi ; Tanaka, Mamoru

Author_Institution

Dept. of Electr. & Electron. Eng., Sophia Univ., Tokyo, Japan

Volume

5

fYear

1999

fDate

1999

Firstpage

559

Abstract

The cooperative and competitive networks proposed by Amari and Arbib are a mathematical model for the winner-take-all process. If this network is implemented by realistic circuit elements, there are many problems. In this paper, we propose cooperative and competitive cellular neural networks by extending the Amari-Arbib model to achieve low power consumption, no oscillation and fast convergence by using piecewise-linear functions. Moreover, the cooperative and competitive cellular neural networks are applied to block matching using basic cellular neural networks

Keywords

cellular neural nets; cooperative systems; piecewise linear techniques; unsupervised learning; Amari-Arbib model; competitive cellular neural networks; convergence; cooperative cellular neural networks; piecewise-linear functions; power consumption; winner-take-all process; Cellular networks; Cellular neural networks; Convergence; Electrons; Energy consumption; Information processing; Integrated circuit interconnections; Magnetooptic recording; Mathematical model; Retina;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-5471-0

Type

conf

DOI

10.1109/ISCAS.1999.777633

Filename

777633