A learning algorithm for time-discrete cellular neural networks

Hubert Harrer, Josef A. Nossek, Fan Zou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

A supervised learning algorithm for time-discrete cellular neural networks is introduced. The algorithm is based on the relaxation method and can be used for the determination of suitable template coefficients. This is done by postulating the subsequent output state of all cells. The relaxation method is able to train the network to a desired parameter insensitivity. Incorporating symmetry constraints leads to a fast convergence. If there exists a solution at all, the relaxation method always terminates after a finite number of iteration steps. The algorithm can also be applied to peceptrons or discrete Hopfield nets containing a comparator characteristic as nonlinearity.

Original languageEnglish
Title of host publication1991 IEEE International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages717-722
Number of pages6
ISBN (Print)0780302273
StatePublished - 1992
Event1991 IEEE International Joint Conference on Neural Networks - IJCNN '91 - Singapore, Singapore
Duration: 18 Nov 199121 Nov 1991

Publication series

Name1991 IEEE International Joint Conference on Neural Networks

Conference

Conference1991 IEEE International Joint Conference on Neural Networks - IJCNN '91
CitySingapore, Singapore
Period18/11/9121/11/91

Fingerprint

Dive into the research topics of 'A learning algorithm for time-discrete cellular neural networks'. Together they form a unique fingerprint.

Cite this