Abstract :
In this paper, global synchronization of linearly coupled neural network (NN) systems with time-varying coupling is investigated. The dynamical behavior of the uncoupled system at each node is general, which can be chaotic or others; the coupling configuration is time varying, i.e., the coupling matrix is not a constant matrix. Based on Lyapunov function method and the specific property of Householder transform, some criteria for the global synchronization are obtained. By these criteria, one can verify whether the coupled system with time-varying coupling is globally synchronized, which is important and useful for both understanding and interpreting synchronization phenomena and designing coupling configuration. Finally, two simulations are given to demonstrate the effectiveness of the theoretical results.
Keywords :
Lyapunov methods; matrix algebra; neural nets; synchronisation; time-varying systems; transforms; Householder transform; Lyapunov function method; global synchronization criteria; linearly coupled neural network system; time-varying coupling matrix; Householder transform; linearly coupled neural network (NN) systems; synchronization; time-varying coupling; Computer Simulation; Feedback; Humans; Linear Models; Neural Networks (Computer); Nonlinear Dynamics; Time Factors;
