Exponential stability of discrete-time neural networks with delay and impulses

Abstract In this paper, we investigate the exponential stability of discrete-time neural networks with impulses and time-varying delay. The discrete-time neural networks are derived by discretizing the corresponding continuous-time counterparts with different discretization methods. The impulses are classified into three classes: input disturbances, stabilizing and “neutral” type – the impulses are neither helpful for stabilizing nor destabilizing the neural networks, and then by using the excellent ideology introduced recently by Chen and Zheng [W.H. Chen, W.X. Zheng, Global exponential stability of impulsive neural networks with variable delay: an LMI approach, IEEE Trans. Circuits Syst. I 56 (6) (2009) 1248–1259], the connections between the impulses and the utilized Lyapunov function are fully explored with respect to each type of impulse. Novel techniques that used to realize the ideology in discrete-time situation are proposed and it is shown that they are essentially different from the continuous-time case. Several criteria for global exponential stability of the discrete-time neural networks are established in terms of matrix inequalities and based on these theoretical results numerical simulations are given to compare the capability of different discretization methods.

[1]  J.Q. Liu,et al.  Apnea Detection Based on Time Delay Neural Network , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[2]  A. G. Naim,et al.  Discrete-time analogues of integrodifferential equations modelling bidirectional neural networks , 2002 .

[3]  Changyin Sun,et al.  Discrete-time analogues of integrodifferential equations modeling neural networks , 2005 .

[4]  Lei Guo,et al.  Dynamics of Continuous-Time Neural Networks and Their Discrete-Time Analogues with Distributed Delays , 2007, ISNN.

[5]  Xiaoqi Yang,et al.  Deriving sufficient conditions for global asymptotic stability of delayed neural networks via nonsmooth analysis , 2004, IEEE Transactions on Neural Networks.

[6]  R. Westervelt,et al.  Stability of analog neural networks with delay. , 1989, Physical review. A, General physics.

[7]  Jinde Cao Periodic oscillation and exponential stability of delayed CNNs , 2000 .

[8]  Wu-Hua Chen,et al.  Global exponential stability for discrete-time neural networks with variable delays , 2006 .

[9]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[10]  Qiang Zhang,et al.  Global exponential convergence analysis of delayed neural networks with time-varying delays , 2003 .

[11]  F. Lavagetto,et al.  Time-delay neural networks for estimating lip movements from speech analysis: a useful tool in audio-video synchronization , 1997, IEEE Trans. Circuits Syst. Video Technol..

[12]  S. Mohamad,et al.  Exponential stability preservation in discrete-time analogues of artificial neural networks with distributed delays , 2008 .

[13]  V. Lakshmikantham,et al.  Theory of Impulsive Differential Equations , 1989, Series in Modern Applied Mathematics.

[14]  Jinde Cao,et al.  Discrete-time bidirectional associative memory neural networks with variable delays , 2005 .

[15]  Jinde Cao,et al.  Stability and periodicity in delayed cellular neural networks with impulsive effects , 2007 .

[16]  Jinde Cao,et al.  Global exponential stability of delayed cellular neural networks with impulses , 2007, Neurocomputing.

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

[18]  Long Cheng,et al.  A Delayed Projection Neural Network for Solving Linear Variational Inequalities , 2009, IEEE Transactions on Neural Networks.

[19]  Sannay Mohamad,et al.  Computer simulations of exponentially convergent networks with large impulses , 2008, Math. Comput. Simul..

[20]  Shumin Fei,et al.  Exponential stability criteria for discrete-time recurrent neural networks with time-varying delay , 2010 .

[21]  K. Gopalsamy,et al.  Exponential stability of continuous-time and discrete-time cellular neural networks with delays , 2003, Appl. Math. Comput..

[22]  Lansun Chen,et al.  Asymptotic behavior of discrete solutions to delayed neural networks with impulses , 2008, Neurocomputing.

[23]  Jinde Cao,et al.  A delayed neural network for solving linear projection equations and its analysis , 2005, IEEE Transactions on Neural Networks.

[24]  Jih-Gau Juang,et al.  Application of time delay neural network to automatic landing control , 2002, Proceedings of the International Conference on Control Applications.

[25]  Daoyi Xu,et al.  Stability Analysis of Delay Neural Networks With Impulsive Effects , 2005, IEEE Trans. Circuits Syst. II Express Briefs.

[26]  Wei Xing Zheng,et al.  Global Exponential Stability of Impulsive Neural Networks With Variable Delay: An LMI Approach , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[27]  Xinzhi Liu,et al.  Uniform asymptotic stability of impulsive delay differential equations , 2001 .

[28]  Toshiyuki Koto,et al.  Stability of IMEX Runge-Kutta methods for delay differential equations , 2008 .

[29]  Hongtao Lu Chaotic attractors in delayed neural networks , 2002 .

[30]  Jinde Cao,et al.  Stability analysis of delayed cellular neural networks , 1998, Neural Networks.

[31]  A. R. Humphries,et al.  Dynamical Systems And Numerical Analysis , 1996 .

[32]  Xudong Ye,et al.  Soft-measuring approach to on-line predict BOD based on PCA time-delay neural network , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[33]  Changyin Sun,et al.  Exponential Periodicity of Continuous-time and Discrete-Time Neural Networks with Delays , 2004, Neural Processing Letters.

[34]  Daoyi Xu,et al.  Delay-dependent stability analysis for impulsive neural networks with time varying delays , 2008, Neurocomputing.