A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI Approach

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 reduc...

Full description

Saved in:
Bibliographic Details
Main Author: Choon Ki Ahn
Format: Article
Language:English
Published: Wiley 2010-01-01
Series:Discrete Dynamics in Nature and Society
Online Access:http://dx.doi.org/10.1155/2010/415895
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228388681220096
author Choon Ki Ahn
author_facet Choon Ki Ahn
author_sort Choon Ki Ahn
collection DOAJ
description 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.
format Article
id doaj-art-204007c3ccf84b97b54d6151bdf3fe8c
institution OA Journals
issn 1026-0226
1607-887X
language English
publishDate 2010-01-01
publisher Wiley
record_format Article
series Discrete Dynamics in Nature and Society
spelling doaj-art-204007c3ccf84b97b54d6151bdf3fe8c2025-08-20T02:04:33ZengWileyDiscrete Dynamics in Nature and Society1026-02261607-887X2010-01-01201010.1155/2010/415895415895A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI ApproachChoon Ki Ahn0Department of Automotive Engineering, Seoul National University of Science and Technology, 172 Gongneung 2-dong, Nowon-gu, Seoul 139-743, Republic of KoreaA 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.http://dx.doi.org/10.1155/2010/415895
spellingShingle Choon Ki Ahn
A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI Approach
Discrete Dynamics in Nature and Society
title A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI Approach
title_full A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI Approach
title_fullStr A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI Approach
title_full_unstemmed A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI Approach
title_short A New Robust Training Law for Dynamic Neural Networks with External Disturbance: An LMI Approach
title_sort new robust training law for dynamic neural networks with external disturbance an lmi approach
url http://dx.doi.org/10.1155/2010/415895
work_keys_str_mv AT choonkiahn anewrobusttraininglawfordynamicneuralnetworkswithexternaldisturbanceanlmiapproach
AT choonkiahn newrobusttraininglawfordynamicneuralnetworkswithexternaldisturbanceanlmiapproach