Stability analysis for delayed Hopfield neural networks

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, an ℋ approach is used to derive a tuning algorithm for delayed Hopfield neural networks. Based on the Lyapunov stability theory, the ℋ learning law is presented to not only guarantee asymptotical stability but also reduce the effect of an external disturbance to an ℋ norm constraint. An existence condition for the proposed learning law is represented in terms of a linear matrix inequality (LMI). An illustrative example is provided to demonstrate the effectiveness of the proposed learning law.

Original languageEnglish
Pages (from-to)203-208
Number of pages6
JournalProceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering
Volume224
Issue number2
DOIs
Publication statusPublished - 2010 Mar 1
Externally publishedYes

Fingerprint

Hopfield neural networks
Linear matrix inequalities
Tuning

Keywords

  • ℋ approach
  • Hopfield neural networks
  • Linear matrix inequality (LMI)
  • Lyapunov stability theory
  • Weight learning

ASJC Scopus subject areas

  • Mechanical Engineering
  • Control and Systems Engineering

Cite this

@article{c11eafafa8d14f31947d915d993c8293,
title = "ℋ∞Stability analysis for delayed Hopfield neural networks",
abstract = "In this paper, an ℋ∞ approach is used to derive a tuning algorithm for delayed Hopfield neural networks. Based on the Lyapunov stability theory, the ℋ∞ learning law is presented to not only guarantee asymptotical stability but also reduce the effect of an external disturbance to an ℋ∞ norm constraint. An existence condition for the proposed learning law is represented in terms of a linear matrix inequality (LMI). An illustrative example is provided to demonstrate the effectiveness of the proposed learning law.",
keywords = "ℋ approach, Hopfield neural networks, Linear matrix inequality (LMI), Lyapunov stability theory, Weight learning",
author = "Ahn, {Choon Ki}",
year = "2010",
month = "3",
day = "1",
doi = "10.1243/09596518JSCE870",
language = "English",
volume = "224",
pages = "203--208",
journal = "Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering",
issn = "0959-6518",
publisher = "SAGE Publications Ltd",
number = "2",

}

TY - JOUR

T1 - ℋ∞Stability analysis for delayed Hopfield neural networks

AU - Ahn, Choon Ki

PY - 2010/3/1

Y1 - 2010/3/1

N2 - In this paper, an ℋ∞ approach is used to derive a tuning algorithm for delayed Hopfield neural networks. Based on the Lyapunov stability theory, the ℋ∞ learning law is presented to not only guarantee asymptotical stability but also reduce the effect of an external disturbance to an ℋ∞ norm constraint. An existence condition for the proposed learning law is represented in terms of a linear matrix inequality (LMI). An illustrative example is provided to demonstrate the effectiveness of the proposed learning law.

AB - In this paper, an ℋ∞ approach is used to derive a tuning algorithm for delayed Hopfield neural networks. Based on the Lyapunov stability theory, the ℋ∞ learning law is presented to not only guarantee asymptotical stability but also reduce the effect of an external disturbance to an ℋ∞ norm constraint. An existence condition for the proposed learning law is represented in terms of a linear matrix inequality (LMI). An illustrative example is provided to demonstrate the effectiveness of the proposed learning law.

KW - ℋ approach

KW - Hopfield neural networks

KW - Linear matrix inequality (LMI)

KW - Lyapunov stability theory

KW - Weight learning

UR - http://www.scopus.com/inward/record.url?scp=77950975124&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950975124&partnerID=8YFLogxK

U2 - 10.1243/09596518JSCE870

DO - 10.1243/09596518JSCE870

M3 - Article

AN - SCOPUS:77950975124

VL - 224

SP - 203

EP - 208

JO - Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering

JF - Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering

SN - 0959-6518

IS - 2

ER -