Premium
On the separating capability of cellular neural networks
Author(s) -
Osuna J. A.,
Moschytz G. S.
Publication year - 1996
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/(sici)1097-007x(199605/06)24:3<253::aid-cta913>3.0.co;2-9
Subject(s) - cellular neural network , artificial neural network , hyperplane , computer science , task (project management) , template , cellular network , binary number , artificial intelligence , time delay neural network , topology (electrical circuits) , pattern recognition (psychology) , algorithm , mathematics , computer network , arithmetic , combinatorics , engineering , programming language , systems engineering
The cellular neural network is able to perform different image‐processing tasks depending on the template values, i.e. the network parameters, used. In the case of linear templates the parameter space is divided into different regions by hyperplanes. Every region is associated with a task, such that all points within that region let the cellular neural network perform the desired task. In this paper a lower and an upper bound for the number of regions that can be separated with binary‐input cellular neural networks are given, thus answering the question of how many different‐tasks such a cellular neural network can perform.