Global Synchronization in an Array of Discrete-Time Neural Networks with Nonlinear Coupling and Time-Varying Delays

A general model for an array of discrete-time neural networks with hybrid coupling is proposed, which is composed of nonlinear coupling and time-varying delays. The coupling terms are described in terms of Lipchitz-type conditions that reflect more realistic dynamical behaviors of coupled systems in practice. The properties of Kronecker product are employed in order to pursue mathematical simplicity of dynamics analysis. On the basis of Lyapunov stability theory, an effective matrix functional is utilized to establish sufficient conditions under which the considered neural networks are globally synchronized. These conditions, which are dependent on the lower bound and the upper bound of the time-varying time delays, are expressed in terms of several linear matrix inequalities (LMIs), and therefore can be easily verified by utilizing the numerically efficient Matlab LMI toolbox. One illustrative example is given to justify the validity and feasibility of the proposed synchronization scheme.

[1]  Zidong Wang,et al.  A delay-dependent LMI approach to dynamics analysis of discrete-time recurrent neural networks with time-varying delays , 2007 .

[2]  Hojjat Adeli,et al.  A neural dynamics model for structural optimization—Theory , 1995 .

[3]  Hojjat Adeli,et al.  Improved spiking neural networks for EEG classification and epilepsy and seizure detection , 2007, Integr. Comput. Aided Eng..

[4]  Hojjat Adeli,et al.  Distributed neural dynamics algorithms for optimization of large steel structures , 1997 .

[5]  Hyo Seon Park,et al.  COUNTERPROPAGATION NEURAL NETWORKS IN STRUCTURAL ENGINEERING , 1995 .

[6]  ASHIF PANAKKAT,et al.  Neural Network Models for Earthquake Magnitude Prediction Using Multiple seismicity Indicators , 2007, Int. J. Neural Syst..

[7]  Hojjat Adeli,et al.  An adaptive conjugate gradient learning algorithm for efficient training of neural networks , 1994 .

[8]  Hojjat Adeli,et al.  Neural Networks in Civil Engineering: 1989–2000 , 2001 .

[9]  Hojjat Adeli,et al.  A parallel genetic/neural network learning algorithm for MIMD shared memory machines , 1994, IEEE Trans. Neural Networks.

[10]  Hojjat Adeli,et al.  Neural network model for rapid forecasting of freeway link travel time , 2003 .

[11]  L. Chua,et al.  Synchronization in an array of linearly coupled dynamical systems , 1995 .

[12]  Zidong Wang,et al.  Exponential stability of delayed recurrent neural networks with Markovian jumping parameters , 2006 .

[13]  Hojjat Adeli,et al.  Optimization of space structures by neural dynamics , 1995, Neural Networks.

[14]  Hojjat Adeli,et al.  Dynamic Wavelet Neural Network for Nonlinear Identification of Highrise Buildings , 2005 .

[15]  Jinde Cao,et al.  Convergence of Discrete-Time Recurrent Neural Networks with Variable Delay , 2005, Int. J. Bifurc. Chaos.

[16]  Jinde Cao,et al.  Global synchronization in arrays of delayed neural networks with constant and delayed coupling , 2006 .

[17]  Hojjat Adeli,et al.  Dynamic Wavelet Neural Network Model for Traffic Flow Forecasting , 2005 .

[18]  H. Adeli,et al.  Dynamic Fuzzy Wavelet Neural Network Model for Structural System Identification , 2006 .