A new robust training law for dynamic neural networks with external disturbance: An LMI approach

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A new robust training law, which is called an input/output-to-state stable training law (IOSSTL), is proposed for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI) formulation, the IOSSTL is presented to not only guarantee exponential stability but also reduce the effect of an external disturbance. It is shown that the IOSSTL can be obtained by solving the LMI, which can be easily facilitated by using some standard numerical packages. Numerical examples are presented to demonstrate the validity of the proposed IOSSTL.

Original languageEnglish
Article number415895
JournalDiscrete Dynamics in Nature and Society
Volume2010
DOIs
Publication statusPublished - 2010 Dec 1
Externally publishedYes

Fingerprint

Dynamic Neural Networks
Linear matrix inequalities
Matrix Inequality
Linear Inequalities
Disturbance
Neural networks
Asymptotic stability
Output
Exponential Stability
Training
Numerical Examples
Formulation
Demonstrate

ASJC Scopus subject areas

  • Modelling and Simulation

Cite this

@article{a6becfb1f496483bbcbc740ae66aafaf,
title = "A new robust training law for dynamic neural networks with external disturbance: An LMI approach",
abstract = "A new robust training law, which is called an input/output-to-state stable training law (IOSSTL), is proposed for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI) formulation, the IOSSTL is presented to not only guarantee exponential stability but also reduce the effect of an external disturbance. It is shown that the IOSSTL can be obtained by solving the LMI, which can be easily facilitated by using some standard numerical packages. Numerical examples are presented to demonstrate the validity of the proposed IOSSTL.",
author = "Ahn, {Choon Ki}",
year = "2010",
month = "12",
day = "1",
doi = "10.1155/2010/415895",
language = "English",
volume = "2010",
journal = "Discrete Dynamics in Nature and Society",
issn = "1026-0226",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - A new robust training law for dynamic neural networks with external disturbance

T2 - An LMI approach

AU - Ahn, Choon Ki

PY - 2010/12/1

Y1 - 2010/12/1

N2 - A new robust training law, which is called an input/output-to-state stable training law (IOSSTL), is proposed for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI) formulation, the IOSSTL is presented to not only guarantee exponential stability but also reduce the effect of an external disturbance. It is shown that the IOSSTL can be obtained by solving the LMI, which can be easily facilitated by using some standard numerical packages. Numerical examples are presented to demonstrate the validity of the proposed IOSSTL.

AB - A new robust training law, which is called an input/output-to-state stable training law (IOSSTL), is proposed for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI) formulation, the IOSSTL is presented to not only guarantee exponential stability but also reduce the effect of an external disturbance. It is shown that the IOSSTL can be obtained by solving the LMI, which can be easily facilitated by using some standard numerical packages. Numerical examples are presented to demonstrate the validity of the proposed IOSSTL.

UR - http://www.scopus.com/inward/record.url?scp=79952150283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952150283&partnerID=8YFLogxK

U2 - 10.1155/2010/415895

DO - 10.1155/2010/415895

M3 - Article

AN - SCOPUS:79952150283

VL - 2010

JO - Discrete Dynamics in Nature and Society

JF - Discrete Dynamics in Nature and Society

SN - 1026-0226

M1 - 415895

ER -