L∞ performance of single and interconnected neural networks with time-varying delay

Choon Ki Ahn; Peng Shi; Ramesh K. Agarwal; Jing Xu

doi:10.1016/j.ins.2016.02.004

L_∞ performance of single and interconnected neural networks with time-varying delay

Choon Ki Ahn, Peng Shi, Ramesh K. Agarwal, Jing Xu

Research output: Contribution to journal › Article › peer-review

37 Citations (Scopus)

Abstract

This paper is concerned with the L_∞ performance analysis problem for time-varying delayed neural networks. First, a condition is proposed for the L_∞ performance of single neural networks with time-varying delay and persistent bounded input based on the Wirtinger-type inequality together with the reciprocal convex approach. Then, sufficient conditions are established to ensure the L_∞ performance of interconnected neural networks with time-varying delay. Numerical examples are provided to show the effectiveness of the presented results.

Original language	English
Pages (from-to)	412-423
Number of pages	12
Journal	Information Sciences
Volume	346-347
DOIs	https://doi.org/10.1016/j.ins.2016.02.004
Publication status	Published - 2016 Jun 10

Bibliographical note

Funding Information:
This work was partially supported by the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2014R1A1A1006101) and partially by “Human Resources program in Energy Technology” of the Korea Institute of Energy Technology Evaluation and Planning (KETEP) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea (No. 20154030200610).

Publisher Copyright:
© 2016 Elsevier Inc.

Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.

Keywords

Feedback interconnection
L performance
Neural network
Time-varying delay

ASJC Scopus subject areas

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

Access to Document

10.1016/j.ins.2016.02.004

Cite this

@article{2f3d57be723440d399986e1ef5efbf2c,

title = "L∞ performance of single and interconnected neural networks with time-varying delay",

abstract = "This paper is concerned with the L∞ performance analysis problem for time-varying delayed neural networks. First, a condition is proposed for the L∞ performance of single neural networks with time-varying delay and persistent bounded input based on the Wirtinger-type inequality together with the reciprocal convex approach. Then, sufficient conditions are established to ensure the L∞ performance of interconnected neural networks with time-varying delay. Numerical examples are provided to show the effectiveness of the presented results.",

keywords = "Feedback interconnection, L performance, Neural network, Time-varying delay",

author = "Ahn, {Choon Ki} and Peng Shi and Agarwal, {Ramesh K.} and Jing Xu",

note = "Funding Information: This work was partially supported by the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2014R1A1A1006101) and partially by “Human Resources program in Energy Technology” of the Korea Institute of Energy Technology Evaluation and Planning (KETEP) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea (No. 20154030200610). Publisher Copyright: {\textcopyright} 2016 Elsevier Inc. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.",

year = "2016",

month = jun,

day = "10",

doi = "10.1016/j.ins.2016.02.004",

language = "English",

volume = "346-347",

pages = "412--423",

journal = "Information Sciences",

issn = "0020-0255",

publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - L∞ performance of single and interconnected neural networks with time-varying delay

AU - Ahn, Choon Ki

AU - Shi, Peng

AU - Agarwal, Ramesh K.

AU - Xu, Jing

N1 - Funding Information: This work was partially supported by the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2014R1A1A1006101) and partially by “Human Resources program in Energy Technology” of the Korea Institute of Energy Technology Evaluation and Planning (KETEP) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea (No. 20154030200610). Publisher Copyright: © 2016 Elsevier Inc. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2016/6/10

Y1 - 2016/6/10

N2 - This paper is concerned with the L∞ performance analysis problem for time-varying delayed neural networks. First, a condition is proposed for the L∞ performance of single neural networks with time-varying delay and persistent bounded input based on the Wirtinger-type inequality together with the reciprocal convex approach. Then, sufficient conditions are established to ensure the L∞ performance of interconnected neural networks with time-varying delay. Numerical examples are provided to show the effectiveness of the presented results.

AB - This paper is concerned with the L∞ performance analysis problem for time-varying delayed neural networks. First, a condition is proposed for the L∞ performance of single neural networks with time-varying delay and persistent bounded input based on the Wirtinger-type inequality together with the reciprocal convex approach. Then, sufficient conditions are established to ensure the L∞ performance of interconnected neural networks with time-varying delay. Numerical examples are provided to show the effectiveness of the presented results.

KW - Feedback interconnection

KW - L performance

KW - Neural network

KW - Time-varying delay

UR - http://www.scopus.com/inward/record.url?scp=84959485464&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959485464&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2016.02.004

DO - 10.1016/j.ins.2016.02.004

M3 - Article

AN - SCOPUS:84959485464

SN - 0020-0255

VL - 346-347

SP - 412

EP - 423

JO - Information Sciences

JF - Information Sciences

ER -