Extended dissipative analysis for neural networks with time-varying delays

Tae H. Lee; Myeong Jin Park; Ju H. Park; Oh Min Kwon; Sang Moon Lee

doi:10.1109/TNNLS.2013.2296514

Extended dissipative analysis for neural networks with time-varying delays

Tae H. Lee
, Myeong Jin Park
, Ju H. Park^*
, Oh Min Kwon
, Sang Moon Lee

^*Corresponding author for this work

Division of Electronic Engineering

Yeungnam University
Chungbuk National University
Daegu University

Research output: Contribution to journal › Journal article › peer-review

190 Scopus citations

Abstract

In this brief, an extended dissipativity analysis was conducted for a neural network with time-varying delays. The concept of the extended dissipativity can be used to solve for the H_∞, L₂ - L_∞, passive, and dissipative performance by adjusting the weighting matrices in a new performance index. In addition, the activation function dividing method is modified by introducing a tuning parameter. Examples are provided to show the effectiveness and less conservatism of the proposed method.

Original language	English
Article number	6712166
Pages (from-to)	1936-1941
Number of pages	6
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	25
Issue number	10
DOIs	https://doi.org/10.1109/TNNLS.2013.2296514
State	Published - 2014.10.1

Keywords

Dissipativity
neural networks
passivity
stability

Access to Document

10.1109/TNNLS.2013.2296514

Cite this

@article{b45b9c299ebe4d139349aef822fa5441,

title = "Extended dissipative analysis for neural networks with time-varying delays",

abstract = "In this brief, an extended dissipativity analysis was conducted for a neural network with time-varying delays. The concept of the extended dissipativity can be used to solve for the H∞, L2 - L∞, passive, and dissipative performance by adjusting the weighting matrices in a new performance index. In addition, the activation function dividing method is modified by introducing a tuning parameter. Examples are provided to show the effectiveness and less conservatism of the proposed method.",

keywords = "Dissipativity, neural networks, passivity, stability",

author = "Lee, \{Tae H.\} and Park, \{Myeong Jin\} and Park, \{Ju H.\} and Kwon, \{Oh Min\} and Lee, \{Sang Moon\}",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2014",

month = oct,

day = "1",

doi = "10.1109/TNNLS.2013.2296514",

language = "English",

volume = "25",

pages = "1936--1941",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

number = "10",

}

TY - JOUR

T1 - Extended dissipative analysis for neural networks with time-varying delays

AU - Lee, Tae H.

AU - Park, Myeong Jin

AU - Park, Ju H.

AU - Kwon, Oh Min

AU - Lee, Sang Moon

PY - 2014/10/1

Y1 - 2014/10/1

N2 - In this brief, an extended dissipativity analysis was conducted for a neural network with time-varying delays. The concept of the extended dissipativity can be used to solve for the H∞, L2 - L∞, passive, and dissipative performance by adjusting the weighting matrices in a new performance index. In addition, the activation function dividing method is modified by introducing a tuning parameter. Examples are provided to show the effectiveness and less conservatism of the proposed method.

AB - In this brief, an extended dissipativity analysis was conducted for a neural network with time-varying delays. The concept of the extended dissipativity can be used to solve for the H∞, L2 - L∞, passive, and dissipative performance by adjusting the weighting matrices in a new performance index. In addition, the activation function dividing method is modified by introducing a tuning parameter. Examples are provided to show the effectiveness and less conservatism of the proposed method.

KW - Dissipativity

KW - neural networks

KW - passivity

KW - stability

UR - https://www.scopus.com/pages/publications/84905048022

U2 - 10.1109/TNNLS.2013.2296514

DO - 10.1109/TNNLS.2013.2296514

M3 - Journal article

C2 - 25291745

AN - SCOPUS:84905048022

SN - 2162-237X

VL - 25

SP - 1936

EP - 1941

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 10

M1 - 6712166

ER -

Extended dissipative analysis for neural networks with time-varying delays

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this