Title :
Exponential synchronization of a class of neural networks with time-varying delays
Author :
Cheng, Chao-Jung ; Liao, Teh-Lu ; Yan, Jun-Juh ; Hwang, Chi-Chuan
Author_Institution :
Dept. of Inf. Eng., Kun Shan Univ., Tainan, Taiwan
Abstract :
This paper aims to present a synchronization scheme for a class of delayed neural networks, which covers the Hopfield neural networks and cellular neural networks with time-varying delays. A feedback control gain matrix is derived to achieve the exponential synchronization of the drive-response structure of neural networks by using the Lyapunov stability theory, and its exponential synchronization condition can be verified if a certain Hamiltonian matrix with no eigenvalues on the imaginary axis. This condition can avoid solving an algebraic Riccati equation. Both the cellular neural networks and Hopfield neural networks with time-varying delays are given as examples for illustration.
Keywords :
Hopfield neural nets; Lyapunov methods; Riccati equations; cellular neural nets; delays; feedback; matrix algebra; synchronisation; time-varying systems; Hamiltonian matrix; Hopfield neural networks; Lyapunov stability theory; algebraic Riccati equation; cellular neural networks; drive-response structure; exponential synchronization; feedback control gain matrix; time-varying delays; Cellular neural networks; Chaotic communication; Communication system control; Eigenvalues and eigenfunctions; Hopfield neural networks; Lyapunov method; Neural networks; Neurons; Nonlinear control systems; Riccati equations; Chaotic systems; Hamiltonian matrix; neural networks; synchronization; Animals; Artificial Intelligence; Biological Clocks; Computer Simulation; Humans; Models, Neurological; Neural Networks (Computer); Nonlinear Dynamics; Synaptic Transmission; Time Factors;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2005.856144
