Global stability of a recurrent neural network for solving pseudomonotone variational inequalities

Xiaolin Hu; Jun Wang

doi:10.1109/ISCAS.2006.1692695

Global stability of a recurrent neural network for solving pseudomonotone variational inequalities

Xiaolin Hu, Jun Wang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

7 Citations (Scopus)

Abstract

Solving variational inequality problems by using neural networks are of great interest in recent years. To date, most work in this direction focus on solving monotone variational inequalities. In this paper, we show that an existing recurrent neural network proposed originally for solving monotone variational inequalities can be used to solve pseudomonotone variational inequalities with proper choice of a system parameter. The global convergence, global asymptotic stability and global exponential stability of the neural network are discussed under various conditions. The existing stability results are thus extended in view of the fact that pseudomonotonicity is a weaker condition than monotonicity. © 2006 IEEE.

Original language	English
Title of host publication	2006 IEEE International Symposium on Circuits and Systems
Subtitle of host publication	Proceedings
Publisher	IEEE
Pages	755-758
ISBN (Electronic)	9780780393905
ISBN (Print)	0-7803-9389-9
DOIs	https://doi.org/10.1109/ISCAS.2006.1692695
Publication status	Published - 2006
Externally published	Yes
Event	2006 IEEE International Symposium on Circuits and Systems (ISCAS 2006): Circuits and Systems: At Crossroads of Life and Technology - Island of Kos, Greece Duration: 21 May 2006 → 24 May 2006

Publication series

Name
ISSN (Print)	0271-4302
ISSN (Electronic)	2158-1525

Conference

Conference	2006 IEEE International Symposium on Circuits and Systems (ISCAS 2006)
Abbreviated title	ISCAS2006
Place	Greece
City	Island of Kos
Period	21/05/06 → 24/05/06

Access Output

10.1109/ISCAS.2006.1692695

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{cf4d5c4c17654b30b59cb46f06feac42,

title = "Global stability of a recurrent neural network for solving pseudomonotone variational inequalities",

abstract = "Solving variational inequality problems by using neural networks are of great interest in recent years. To date, most work in this direction focus on solving monotone variational inequalities. In this paper, we show that an existing recurrent neural network proposed originally for solving monotone variational inequalities can be used to solve pseudomonotone variational inequalities with proper choice of a system parameter. The global convergence, global asymptotic stability and global exponential stability of the neural network are discussed under various conditions. The existing stability results are thus extended in view of the fact that pseudomonotonicity is a weaker condition than monotonicity. {\textcopyright} 2006 IEEE.",

author = "Xiaolin Hu and Jun Wang",

year = "2006",

doi = "10.1109/ISCAS.2006.1692695",

language = "English",

isbn = "0-7803-9389-9",

publisher = "IEEE",

pages = "755--758",

booktitle = "2006 IEEE International Symposium on Circuits and Systems",

address = "United States",

note = "2006 IEEE International Symposium on Circuits and Systems (ISCAS 2006) : Circuits and Systems: At Crossroads of Life and Technology, ISCAS2006 ; Conference date: 21-05-2006 Through 24-05-2006",

}

Global stability of a recurrent neural network for solving pseudomonotone variational inequalities. / Hu, Xiaolin; Wang, Jun.
2006 IEEE International Symposium on Circuits and Systems: Proceedings. IEEE, 2006. p. 755-758.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Global stability of a recurrent neural network for solving pseudomonotone variational inequalities

AU - Hu, Xiaolin

AU - Wang, Jun

PY - 2006

Y1 - 2006

N2 - Solving variational inequality problems by using neural networks are of great interest in recent years. To date, most work in this direction focus on solving monotone variational inequalities. In this paper, we show that an existing recurrent neural network proposed originally for solving monotone variational inequalities can be used to solve pseudomonotone variational inequalities with proper choice of a system parameter. The global convergence, global asymptotic stability and global exponential stability of the neural network are discussed under various conditions. The existing stability results are thus extended in view of the fact that pseudomonotonicity is a weaker condition than monotonicity. © 2006 IEEE.

AB - Solving variational inequality problems by using neural networks are of great interest in recent years. To date, most work in this direction focus on solving monotone variational inequalities. In this paper, we show that an existing recurrent neural network proposed originally for solving monotone variational inequalities can be used to solve pseudomonotone variational inequalities with proper choice of a system parameter. The global convergence, global asymptotic stability and global exponential stability of the neural network are discussed under various conditions. The existing stability results are thus extended in view of the fact that pseudomonotonicity is a weaker condition than monotonicity. © 2006 IEEE.

UR - http://www.scopus.com/inward/record.url?scp=34547339197&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-34547339197&origin=recordpage

U2 - 10.1109/ISCAS.2006.1692695

DO - 10.1109/ISCAS.2006.1692695

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0-7803-9389-9

SP - 755

EP - 758

BT - 2006 IEEE International Symposium on Circuits and Systems

PB - IEEE

T2 - 2006 IEEE International Symposium on Circuits and Systems (ISCAS 2006)

Y2 - 21 May 2006 through 24 May 2006

ER -

Global stability of a recurrent neural network for solving pseudomonotone variational inequalities

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this