Global asymptotic and exponential stability of a dynamic neural system with asymmetric connection weights

Youshen Xia; Jun Wang

doi:10.1109/9.917666

Global asymptotic and exponential stability of a dynamic neural system with asymmetric connection weights

Youshen Xia, Jun Wang

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

44 Citations (Scopus)

Abstract

Recently, a dynamic neural system was presented and analyzed due to its good performance in optimization computation and low complexity for implementation. The global asymptotic stability of such a dynamic neural system with symmetric connection weights was well studied. In this note, based on a new Lyapunov function, we investigate the global asymptotic stability of the dynamic neural system with asymmetric connection weights. Since the dynamic neural system with asymmetric weights is more general than that with symmetric ones, the new results are significant in both theory and applications. Specially, the new result can cover the asymptotic stability results of linear systems as special cases.

Original language	English
Pages (from-to)	635-638
Journal	IEEE Transactions on Automatic Control
Volume	46
Issue number	4
DOIs	https://doi.org/10.1109/9.917666
Publication status	Published - Apr 2001
Externally published	Yes

Research Keywords

Asymmetric connection weights
Global asymptotic stability
Neural networks

Access Output

10.1109/9.917666

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{3a0347f2fa6c49d792991abc4ec7adfc,

title = "Global asymptotic and exponential stability of a dynamic neural system with asymmetric connection weights",

abstract = "Recently, a dynamic neural system was presented and analyzed due to its good performance in optimization computation and low complexity for implementation. The global asymptotic stability of such a dynamic neural system with symmetric connection weights was well studied. In this note, based on a new Lyapunov function, we investigate the global asymptotic stability of the dynamic neural system with asymmetric connection weights. Since the dynamic neural system with asymmetric weights is more general than that with symmetric ones, the new results are significant in both theory and applications. Specially, the new result can cover the asymptotic stability results of linear systems as special cases.",

keywords = "Asymmetric connection weights, Global asymptotic stability, Neural networks",

author = "Youshen Xia and Jun Wang",

year = "2001",

month = apr,

doi = "10.1109/9.917666",

language = "English",

volume = "46",

pages = "635--638",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

publisher = "IEEE",

number = "4",

}

TY - JOUR

T1 - Global asymptotic and exponential stability of a dynamic neural system with asymmetric connection weights

AU - Xia, Youshen

AU - Wang, Jun

PY - 2001/4

Y1 - 2001/4

N2 - Recently, a dynamic neural system was presented and analyzed due to its good performance in optimization computation and low complexity for implementation. The global asymptotic stability of such a dynamic neural system with symmetric connection weights was well studied. In this note, based on a new Lyapunov function, we investigate the global asymptotic stability of the dynamic neural system with asymmetric connection weights. Since the dynamic neural system with asymmetric weights is more general than that with symmetric ones, the new results are significant in both theory and applications. Specially, the new result can cover the asymptotic stability results of linear systems as special cases.

AB - Recently, a dynamic neural system was presented and analyzed due to its good performance in optimization computation and low complexity for implementation. The global asymptotic stability of such a dynamic neural system with symmetric connection weights was well studied. In this note, based on a new Lyapunov function, we investigate the global asymptotic stability of the dynamic neural system with asymmetric connection weights. Since the dynamic neural system with asymmetric weights is more general than that with symmetric ones, the new results are significant in both theory and applications. Specially, the new result can cover the asymptotic stability results of linear systems as special cases.

KW - Asymmetric connection weights

KW - Global asymptotic stability

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=0035307304&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0035307304&origin=recordpage

U2 - 10.1109/9.917666

DO - 10.1109/9.917666

M3 - RGC 21 - Publication in refereed journal

SN - 0018-9286

VL - 46

SP - 635

EP - 638

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 4

ER -

Global asymptotic and exponential stability of a dynamic neural system with asymmetric connection weights

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this