Please use this identifier to cite or link to this item: http://hdl.handle.net/11452/28605
Title: New global robust stability condition for uncertain neural networks with time delays
Authors: Arık, Sabri
Uludağ Üniversitesi/Mühendislik Fakültesi/Elektrik Elektronik Mühendisliği Bölümü.
Özcan, Neyir
7003726676
Keywords: Delayed neural networks
Lyapunov functionals
Stability analysis
Matrix analysis
Varying delays
Exponential Stability
Criteria
Matrices
Norm
Computer science
Neural networks
Global asymptotic stability
Global robust stability
Lyapunov-Krasovskii functionals
Uncertain neural networks
Robustness (control systems)
Issue Date: 22-Oct-2014
Publisher: Elsevier
Citation: Özcan, N. ve Arık, S. (2014). "New global robust stability condition for uncertain neural networks with time delays". Neurocomputing, 142(Special Issue), 267-274.
Abstract: In this paper, we investigate the robust stability problem for the class of delayed neural networks under parameter uncertainties and with respect to nondecreasing activation functions. Firstly, some new upper bound values for the elements of the intervalized connection matrices are obtained. Then, a new sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point for this class of neural networks is derived by constructing an appropriate Lyapunov-Krasovskii functional and employing homeomorphism mapping theorem. The obtained result establishes a new relationship between the network parameters of the neural system and it is independent of the delay parameters. A comparative numerical example is also given to show the effectiveness, advantages and less conservatism of the proposed result.
URI: https://doi.org/10.1016/j.neucom.2014.04.040
https://www.sciencedirect.com/science/article/pii/S0925231214006328
http://hdl.handle.net/11452/28605
ISSN: 0925-2312
1872-8286
Appears in Collections:Scopus
Web of Science

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.