H∞ stability of neural networks switched at an arbitrary time

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This article proposes a novel approach to stability analysis of neural networks switched at an arbitrary time. First, a new condition for H∞ stability of switched neural networks is proposed. Second, a new H∞ stability condition in the form of linear matrix inequality (LMI) for these neural networks is proposed. These conditions ensure to reduce the H∞ norm from the external input to the state vector within a disturbance attenuation level. Without the external input, the proposed conditions also guarantee asymptotic stability.

Original languageEnglish
Pages (from-to)38-44
Number of pages7
JournalInternational Journal of Artificial Intelligence
Volume8
Issue number12 S
Publication statusPublished - 2012 Mar 1
Externally publishedYes

Fingerprint

Neural networks
Asymptotic stability
Linear matrix inequalities

Keywords

  • H8 stability
  • Linear matrix inequality (LMI)
  • Switched neural networks

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

H∞ stability of neural networks switched at an arbitrary time. / Ahn, Choon Ki.

In: International Journal of Artificial Intelligence, Vol. 8, No. 12 S, 01.03.2012, p. 38-44.

Research output: Contribution to journalArticle

@article{30579f78fb4c40d094b96f544826cf8a,
title = "H∞ stability of neural networks switched at an arbitrary time",
abstract = "This article proposes a novel approach to stability analysis of neural networks switched at an arbitrary time. First, a new condition for H∞ stability of switched neural networks is proposed. Second, a new H∞ stability condition in the form of linear matrix inequality (LMI) for these neural networks is proposed. These conditions ensure to reduce the H∞ norm from the external input to the state vector within a disturbance attenuation level. Without the external input, the proposed conditions also guarantee asymptotic stability.",
keywords = "H8 stability, Linear matrix inequality (LMI), Switched neural networks",
author = "Ahn, {Choon Ki}",
year = "2012",
month = "3",
day = "1",
language = "English",
volume = "8",
pages = "38--44",
journal = "International Journal of Artificial Intelligence",
issn = "0974-0635",
publisher = "Indian Society for Development and Environment Research",
number = "12 S",

}

TY - JOUR

T1 - H∞ stability of neural networks switched at an arbitrary time

AU - Ahn, Choon Ki

PY - 2012/3/1

Y1 - 2012/3/1

N2 - This article proposes a novel approach to stability analysis of neural networks switched at an arbitrary time. First, a new condition for H∞ stability of switched neural networks is proposed. Second, a new H∞ stability condition in the form of linear matrix inequality (LMI) for these neural networks is proposed. These conditions ensure to reduce the H∞ norm from the external input to the state vector within a disturbance attenuation level. Without the external input, the proposed conditions also guarantee asymptotic stability.

AB - This article proposes a novel approach to stability analysis of neural networks switched at an arbitrary time. First, a new condition for H∞ stability of switched neural networks is proposed. Second, a new H∞ stability condition in the form of linear matrix inequality (LMI) for these neural networks is proposed. These conditions ensure to reduce the H∞ norm from the external input to the state vector within a disturbance attenuation level. Without the external input, the proposed conditions also guarantee asymptotic stability.

KW - H8 stability

KW - Linear matrix inequality (LMI)

KW - Switched neural networks

UR - http://www.scopus.com/inward/record.url?scp=84863596335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863596335&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84863596335

VL - 8

SP - 38

EP - 44

JO - International Journal of Artificial Intelligence

JF - International Journal of Artificial Intelligence

SN - 0974-0635

IS - 12 S

ER -