Stability of Multi-layer Cellular Neural/Nonlinear Networks

Levente Török, T. Roska

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

We have found a formalism that lets us present generalizations of several stability theorems (see Chua & Roska, 1990; Chua & Wu, 1992; Gilli, 1993; Forti, 2002] on Multi-Layer Cellular Neural/Nonlinear Networks (MLCNN) formerly claimed for Single-Layer Cellular Neural/Nonlinear Networks (CNN). The theorems were selected with special regard to usefulness in engineering applications. Hence, in contrast to many works considering stability on recurrent neural networks, the criteria of the new theorems have clear indications that are easy to verify directly on the template values. Proofs of six new theorems on 2-Layer CNNs (2LCNN) related to symmetric, τ-symmetric, nonsymmetric, τ-nonsymmetric, and sign-symmetric cases are given. Furthermore, a theorem with a proof on a MLCNN with arbitrary template size and arbitrary layer number in relation to the sign-symmetric theorem is given, along with a conjecture for the one-dimensional, two-layer, nonreciprocal case.

Original languageEnglish
Pages (from-to)3567-3586
Number of pages20
JournalInternational Journal of Bifurcation and Chaos in Applied Sciences and Engineering
Volume14
Issue number10
DOIs
Publication statusPublished - Oct 2004

Fingerprint

Nonlinear networks
Multilayer
Theorem
Recurrent neural networks
Template
Stability Theorem
Recurrent Neural Networks
Arbitrary
Engineering Application
Verify

Keywords

  • CACE
  • Multi-layer CNN
  • Recurrent network stability

ASJC Scopus subject areas

  • General
  • Applied Mathematics

Cite this

Stability of Multi-layer Cellular Neural/Nonlinear Networks. / Török, Levente; Roska, T.

In: International Journal of Bifurcation and Chaos in Applied Sciences and Engineering, Vol. 14, No. 10, 10.2004, p. 3567-3586.

Research output: Contribution to journalArticle

@article{73fddd5e00ac46a7ad6ca93640b057c8,
title = "Stability of Multi-layer Cellular Neural/Nonlinear Networks",
abstract = "We have found a formalism that lets us present generalizations of several stability theorems (see Chua & Roska, 1990; Chua & Wu, 1992; Gilli, 1993; Forti, 2002] on Multi-Layer Cellular Neural/Nonlinear Networks (MLCNN) formerly claimed for Single-Layer Cellular Neural/Nonlinear Networks (CNN). The theorems were selected with special regard to usefulness in engineering applications. Hence, in contrast to many works considering stability on recurrent neural networks, the criteria of the new theorems have clear indications that are easy to verify directly on the template values. Proofs of six new theorems on 2-Layer CNNs (2LCNN) related to symmetric, τ-symmetric, nonsymmetric, τ-nonsymmetric, and sign-symmetric cases are given. Furthermore, a theorem with a proof on a MLCNN with arbitrary template size and arbitrary layer number in relation to the sign-symmetric theorem is given, along with a conjecture for the one-dimensional, two-layer, nonreciprocal case.",
keywords = "CACE, Multi-layer CNN, Recurrent network stability",
author = "Levente T{\"o}r{\"o}k and T. Roska",
year = "2004",
month = "10",
doi = "10.1142/S0218127404011582",
language = "English",
volume = "14",
pages = "3567--3586",
journal = "International Journal of Bifurcation and Chaos in Applied Sciences and Engineering",
issn = "0218-1274",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "10",

}

TY - JOUR

T1 - Stability of Multi-layer Cellular Neural/Nonlinear Networks

AU - Török, Levente

AU - Roska, T.

PY - 2004/10

Y1 - 2004/10

N2 - We have found a formalism that lets us present generalizations of several stability theorems (see Chua & Roska, 1990; Chua & Wu, 1992; Gilli, 1993; Forti, 2002] on Multi-Layer Cellular Neural/Nonlinear Networks (MLCNN) formerly claimed for Single-Layer Cellular Neural/Nonlinear Networks (CNN). The theorems were selected with special regard to usefulness in engineering applications. Hence, in contrast to many works considering stability on recurrent neural networks, the criteria of the new theorems have clear indications that are easy to verify directly on the template values. Proofs of six new theorems on 2-Layer CNNs (2LCNN) related to symmetric, τ-symmetric, nonsymmetric, τ-nonsymmetric, and sign-symmetric cases are given. Furthermore, a theorem with a proof on a MLCNN with arbitrary template size and arbitrary layer number in relation to the sign-symmetric theorem is given, along with a conjecture for the one-dimensional, two-layer, nonreciprocal case.

AB - We have found a formalism that lets us present generalizations of several stability theorems (see Chua & Roska, 1990; Chua & Wu, 1992; Gilli, 1993; Forti, 2002] on Multi-Layer Cellular Neural/Nonlinear Networks (MLCNN) formerly claimed for Single-Layer Cellular Neural/Nonlinear Networks (CNN). The theorems were selected with special regard to usefulness in engineering applications. Hence, in contrast to many works considering stability on recurrent neural networks, the criteria of the new theorems have clear indications that are easy to verify directly on the template values. Proofs of six new theorems on 2-Layer CNNs (2LCNN) related to symmetric, τ-symmetric, nonsymmetric, τ-nonsymmetric, and sign-symmetric cases are given. Furthermore, a theorem with a proof on a MLCNN with arbitrary template size and arbitrary layer number in relation to the sign-symmetric theorem is given, along with a conjecture for the one-dimensional, two-layer, nonreciprocal case.

KW - CACE

KW - Multi-layer CNN

KW - Recurrent network stability

UR - http://www.scopus.com/inward/record.url?scp=10444223033&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10444223033&partnerID=8YFLogxK

U2 - 10.1142/S0218127404011582

DO - 10.1142/S0218127404011582

M3 - Article

AN - SCOPUS:10444223033

VL - 14

SP - 3567

EP - 3586

JO - International Journal of Bifurcation and Chaos in Applied Sciences and Engineering

JF - International Journal of Bifurcation and Chaos in Applied Sciences and Engineering

SN - 0218-1274

IS - 10

ER -