Title :
On Stability of Neural Networks by a Lyapunov Functional-Based Approach
Author :
Xu, Jun ; Pi, Daoying ; Cao, Yong-Yan ; Zhong, Shouming
Author_Institution :
Nat. Lab. of Ind. Control Technol., Zhejiang Univ., Hangzhou
fDate :
4/1/2007 12:00:00 AM
Abstract :
In this paper, a new Lyapunov functional-based method is proposed for the stability analysis of delayed cellular neural networks (DCNN). Global exponential stability conditions are obtained for the general DCNN, the Hopfield neural networks (HNNs), and delayed HNNs with monotonic nondecreasing and nonconstant activation functions
Keywords :
Hopfield neural nets; Lyapunov methods; asymptotic stability; Lyapunov functional-based approach; activation functions; delayed Hopfield neural networks; delayed cellular neural networks; global exponential stability conditions; neural network stability; stability analysis; Asymptotic stability; Cellular neural networks; Delay effects; Hopfield neural networks; Industrial control; Laboratories; Neural networks; Signal processing; Stability analysis; Stability criteria; Delayed cellular neural networks (DCNNs); Lyapunov functional; global exponential stability;
Journal_Title :
Circuits and Systems I: Regular Papers, IEEE Transactions on
DOI :
10.1109/TCSI.2007.890604
