Minimizing the effects of parameter deviations on cellular neural networks

Krzysztof Slot, Leon O. Chua, T. Roska

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The sensitivity of cellular neural networks (CNN) against random parameter deviations is discussed in detail. For different CNN with erroneous parameters the probability is estimated that all cell outputs converge to the same stable fixpoint of the corresponding error free CNN. These results are compared with approximations based on a statistical independence assumption. The influence of deviated parameters is demonstrated for different image processing templates. We propose a new parameter learning method for minimizing the effect of template and bias deviations. In all treated cases a significant improvement can be observed by using this method.

Original languageEnglish
Pages (from-to)77-86
Number of pages10
JournalInternational Journal of Circuit Theory and Applications
Volume27
Issue number1
DOIs
Publication statusPublished - Jan 1999

Fingerprint

Cellular neural networks
Cellular Networks
Deviation
Neural Networks
Template
Statistical Independence
Parameter Learning
Random Parameters
Fixpoint
Image Processing
Image processing
Converge
Output
Cell
Approximation

Keywords

  • Cellular neural networks
  • Parameter deviations

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Minimizing the effects of parameter deviations on cellular neural networks. / Slot, Krzysztof; Chua, Leon O.; Roska, T.

In: International Journal of Circuit Theory and Applications, Vol. 27, No. 1, 01.1999, p. 77-86.

Research output: Contribution to journalArticle

@article{a171361f15fa453aa30304459eb79f60,
title = "Minimizing the effects of parameter deviations on cellular neural networks",
abstract = "The sensitivity of cellular neural networks (CNN) against random parameter deviations is discussed in detail. For different CNN with erroneous parameters the probability is estimated that all cell outputs converge to the same stable fixpoint of the corresponding error free CNN. These results are compared with approximations based on a statistical independence assumption. The influence of deviated parameters is demonstrated for different image processing templates. We propose a new parameter learning method for minimizing the effect of template and bias deviations. In all treated cases a significant improvement can be observed by using this method.",
keywords = "Cellular neural networks, Parameter deviations",
author = "Krzysztof Slot and Chua, {Leon O.} and T. Roska",
year = "1999",
month = "1",
doi = "10.1002/(SICI)1097-007X(199901/02)27:1<77::AID-CTA41>3.0.CO;2-0",
language = "English",
volume = "27",
pages = "77--86",
journal = "International Journal of Circuit Theory and Applications",
issn = "0098-9886",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - Minimizing the effects of parameter deviations on cellular neural networks

AU - Slot, Krzysztof

AU - Chua, Leon O.

AU - Roska, T.

PY - 1999/1

Y1 - 1999/1

N2 - The sensitivity of cellular neural networks (CNN) against random parameter deviations is discussed in detail. For different CNN with erroneous parameters the probability is estimated that all cell outputs converge to the same stable fixpoint of the corresponding error free CNN. These results are compared with approximations based on a statistical independence assumption. The influence of deviated parameters is demonstrated for different image processing templates. We propose a new parameter learning method for minimizing the effect of template and bias deviations. In all treated cases a significant improvement can be observed by using this method.

AB - The sensitivity of cellular neural networks (CNN) against random parameter deviations is discussed in detail. For different CNN with erroneous parameters the probability is estimated that all cell outputs converge to the same stable fixpoint of the corresponding error free CNN. These results are compared with approximations based on a statistical independence assumption. The influence of deviated parameters is demonstrated for different image processing templates. We propose a new parameter learning method for minimizing the effect of template and bias deviations. In all treated cases a significant improvement can be observed by using this method.

KW - Cellular neural networks

KW - Parameter deviations

UR - http://www.scopus.com/inward/record.url?scp=0032600085&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032600085&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1097-007X(199901/02)27:1<77::AID-CTA41>3.0.CO;2-0

DO - 10.1002/(SICI)1097-007X(199901/02)27:1<77::AID-CTA41>3.0.CO;2-0

M3 - Article

VL - 27

SP - 77

EP - 86

JO - International Journal of Circuit Theory and Applications

JF - International Journal of Circuit Theory and Applications

SN - 0098-9886

IS - 1

ER -