Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay

Research output: Contribution to journalArticle

65 Citations (Scopus)

Abstract

In this paper, we propose a new passive weight learning law for switched Hopfield neural networks with time-delay under parametric uncertainty. Based on the proposed passive learning law, some new stability results, such as asymptotical stability, input-to-state stability (ISS), and bounded input-bounded output (BIBO) stability, are presented. An existence condition for the passive weight learning law of switched Hopfield neural networks is expressed in terms of strict linear matrix inequality (LMI). Finally, numerical examples are provided to illustrate our results.

Original languageEnglish
Pages (from-to)4582-4594
Number of pages13
JournalInformation Sciences
Volume180
Issue number23
DOIs
Publication statusPublished - 2010 Dec 1
Externally publishedYes

Fingerprint

Hopfield neural networks
Hopfield Neural Network
Time Delay
Time delay
Asymptotical Stability
Parametric Uncertainty
Matrix Inequality
Linear Inequalities
Linear matrix inequalities
Numerical Examples
Output
Learning
Hopfield neural network

Keywords

  • Input-to-state stability (ISS)
  • Linear matrix inequality (LMI)
  • Lyapunov-Krasovskii stability theory
  • Passive weight learning law
  • Switched Hopfield neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Information Systems and Management
  • Control and Systems Engineering
  • Theoretical Computer Science

Cite this

Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay. / Ahn, Choon Ki.

In: Information Sciences, Vol. 180, No. 23, 01.12.2010, p. 4582-4594.

Research output: Contribution to journalArticle

@article{282e41914a9c4bbdbc082a8c8eb41292,
title = "Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay",
abstract = "In this paper, we propose a new passive weight learning law for switched Hopfield neural networks with time-delay under parametric uncertainty. Based on the proposed passive learning law, some new stability results, such as asymptotical stability, input-to-state stability (ISS), and bounded input-bounded output (BIBO) stability, are presented. An existence condition for the passive weight learning law of switched Hopfield neural networks is expressed in terms of strict linear matrix inequality (LMI). Finally, numerical examples are provided to illustrate our results.",
keywords = "Input-to-state stability (ISS), Linear matrix inequality (LMI), Lyapunov-Krasovskii stability theory, Passive weight learning law, Switched Hopfield neural networks",
author = "Ahn, {Choon Ki}",
year = "2010",
month = "12",
day = "1",
doi = "10.1016/j.ins.2010.08.014",
language = "English",
volume = "180",
pages = "4582--4594",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",
number = "23",

}

TY - JOUR

T1 - Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay

AU - Ahn, Choon Ki

PY - 2010/12/1

Y1 - 2010/12/1

N2 - In this paper, we propose a new passive weight learning law for switched Hopfield neural networks with time-delay under parametric uncertainty. Based on the proposed passive learning law, some new stability results, such as asymptotical stability, input-to-state stability (ISS), and bounded input-bounded output (BIBO) stability, are presented. An existence condition for the passive weight learning law of switched Hopfield neural networks is expressed in terms of strict linear matrix inequality (LMI). Finally, numerical examples are provided to illustrate our results.

AB - In this paper, we propose a new passive weight learning law for switched Hopfield neural networks with time-delay under parametric uncertainty. Based on the proposed passive learning law, some new stability results, such as asymptotical stability, input-to-state stability (ISS), and bounded input-bounded output (BIBO) stability, are presented. An existence condition for the passive weight learning law of switched Hopfield neural networks is expressed in terms of strict linear matrix inequality (LMI). Finally, numerical examples are provided to illustrate our results.

KW - Input-to-state stability (ISS)

KW - Linear matrix inequality (LMI)

KW - Lyapunov-Krasovskii stability theory

KW - Passive weight learning law

KW - Switched Hopfield neural networks

UR - http://www.scopus.com/inward/record.url?scp=77956619247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956619247&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2010.08.014

DO - 10.1016/j.ins.2010.08.014

M3 - Article

VL - 180

SP - 4582

EP - 4594

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

IS - 23

ER -