Analysis on stability for generalized neural networks with time-varying delays via second-order orthogonal polynomials-based integral inequality

Seok Young Lee, Min Su Kim, Chaneun Park, Poogyeon Park

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper aims at improving stability criteria for generalized neural networks with time-varying delays by adaptively utilizing a second-order orthogonal polynomials-based integral inequality. Also, to fully employ the integral inequality, stability criteria are developed with not only integral state terms but also their interval-normalized terms. Additionally, general activation function conditions are introduced to enlarge feasible region of stability criteria. A numerical example shows the effectiveness of the proposed stability criteria in terms of maximum delay bounds.

Original languageEnglish
Title of host publicationICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings
PublisherIEEE Computer Society
Pages432-436
Number of pages5
ISBN (Electronic)9788993215137
DOIs
StatePublished - 13 Dec 2017
Event17th International Conference on Control, Automation and Systems, ICCAS 2017 - Jeju, Korea, Republic of
Duration: 18 Oct 201721 Oct 2017

Publication series

NameInternational Conference on Control, Automation and Systems
Volume2017-October
ISSN (Print)1598-7833

Conference

Conference17th International Conference on Control, Automation and Systems, ICCAS 2017
Country/TerritoryKorea, Republic of
CityJeju
Period18/10/1721/10/17

Keywords

  • Generalized neural networks
  • Lyapunov-Krasovskii approach
  • Stability analysis
  • Time-varying delays

Fingerprint

Dive into the research topics of 'Analysis on stability for generalized neural networks with time-varying delays via second-order orthogonal polynomials-based integral inequality'. Together they form a unique fingerprint.

Cite this