An approach to the design of space-varying cellular neural networks for associative memories

Author

Brucoli, Michele ; Carnimeo, Leonarda ; Grassi, Giuseppe

Author_Institution

Dipartimento di Elettrotecnica & Elettronica, Politecnico di Bari, Italy

Volume

1

fYear

1994

fDate

3-5 Aug 1994

Firstpage

549

Abstract

In this work a design of a space-varying cellular neural network (CNN) in order to behave as an associative memory is presented. To this purpose, a new class of space-varying cellular neural networks with a nonsymmetric interconnection structure is considered. A stability analysis is firstly carried out. Then, a learning algorithm, based on the relaxation method, is used to compute the feedback parameters of the considered network. Simulation tests are reported to confirm the validity of the suggested approach

Keywords

cellular neural nets; content-addressable storage; learning (artificial intelligence); stability; associative memories; design; feedback parameters; learning algorithm; nonsymmetric interconnection structure; relaxation method; simulation; space-varying cellular neural networks; stability analysis; Associative memory; Cellular neural networks; Computer networks; Equations; Integrated circuit interconnections; Neural networks; Relaxation methods; Sparse matrices; Stability analysis; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1994., Proceedings of the 37th Midwest Symposium on

Conference_Location

Lafayette, LA

Print_ISBN

0-7803-2428-5

Type

conf

DOI

10.1109/MWSCAS.1994.519298

Filename

519298