Stability and Synchronization Analysis of Discrete-Time Delayed Neural Networks with Discontinuous Activations

In this paper, both stability and synchronization of discrete-time delayed neural networks with discontinuous activations are investigated. By means of functional differential inclusions and Kakutani’s fixed point theorem, conditions are derived to ensure the existence and uniqueness of the solution. Besides, we obtain some novel sufficient conditions for global attractivity and asymptotic stability of the discontinuous discrete-time neural networks via the Halanay-type inequality and the comparison principle. Furthermore, under weaker conditions than Lipschitz conditions, we also select two different controllers to guarantee synchronization of the discrete-time neural networks with discontinuous activations. Finally, some examples with numerical simulation are given to demonstrate the effectiveness of the obtained results.

[1]  Huaguang Zhang,et al.  Dissipativity Analysis for Stochastic Memristive Neural Networks With Time-Varying Delays: A Discrete-Time Case , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Lihong Huang,et al.  New exponential synchronization criteria for time-varying delayed neural networks with discontinuous activations , 2015, Neural Networks.

[3]  Feng-Xian Wang,et al.  Stability and synchronization analysis of neural networks via Halanay-type inequality , 2017, J. Comput. Appl. Math..

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

[5]  Yonggang Chen,et al.  Synchronization of delayed discrete-time neural networks subject to saturated time-delay feedback , 2016, Neurocomputing.

[6]  Sitian Qin,et al.  Global exponential stability of uncertain neural networks with discontinuous Lurie-type activation and mixed delays , 2016, Neurocomputing.

[7]  Leon O. Chua,et al.  Neural networks for nonlinear programming , 1988 .

[8]  Aleksej F. Filippov,et al.  Differential Equations with Discontinuous Righthand Sides , 1988, Mathematics and Its Applications.

[9]  Lihong Huang,et al.  Periodicity and multi-periodicity of generalized Cohen–Grossberg neural networks via functional differential inclusions , 2016 .

[10]  Yue Zhao,et al.  Assessing the Influence of an Individual Event in Complex Fault Spreading Network Based on Dynamic Uncertain Causality Graph , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Haijun Jiang,et al.  New results on exponential synchronization of memristor-based neural networks with discontinuous neuron activations , 2016, Neural Networks.

[12]  Jurang Yan,et al.  Oscillation and Stability of Linear Impulsive Delay Differential Equations , 1998 .

[13]  Lihong Huang,et al.  Existence and global asymptotic stability of periodic solution for discrete and distributed time-varying delayed neural networks with discontinuous activations , 2011, Neurocomputing.

[14]  Fuad E. Alsaadi,et al.  On passivity and robust passivity for discrete-time stochastic neural networks with randomly occurring mixed time delays , 2017, Neural Computing and Applications.

[15]  Ju H. Park,et al.  Synchronization of discrete-time complex dynamical networks with interval time-varying delays via non-fragile controller with randomly occurring perturbation , 2014, J. Frankl. Inst..

[16]  Jinde Cao,et al.  Robust fixed-time synchronization of delayed Cohen-Grossberg neural networks , 2016, Neural Networks.

[17]  Haijun Jiang,et al.  Convergence behavior of delayed discrete cellular neural network without periodic coefficients , 2014, Neural Networks.

[18]  Jinde Cao.  New results concerning exponential stability and periodic solutions of delayed cellular neural networks , 2003 .

[19]  M. Forti,et al.  Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipschitz activations , 2006 .

[20]  Dong Xie,et al.  Global exponential stability of periodic solution for delayed complex-valued neural networks with impulses , 2016, Neurocomputing.

[21]  Chunhai Kou,et al.  Stability analysis by Krasnoselskii's fixed point theorem for nonlinear fractional differential equations , 2015, Appl. Math. Comput..

[22]  Qing-Long Han,et al.  Global asymptotic stability analysis for delayed neural networks using a matrix-based quadratic convex approach , 2014, Neural Networks.

[23]  David H. Eberly.  Ordinary Difference Equations , 2010 .

[24]  Zhenyuan Guo,et al.  Dynamical behavior of delayed Hopfield neural networks with discontinuous activations , 2009 .

[25]  M. Forti,et al.  Global convergence of neural networks with discontinuous neuron activations , 2003 .

[26]  Young Hoon Joo,et al.  Robust extended dissipativity criteria for discrete-time uncertain neural networks with time-varying delays , 2017, Neural Computing and Applications.

[27]  K. Gopalsamy,et al.  Dynamics of a class of discete-time neural networks and their comtinuous-time counterparts , 2000 .

[28]  Yanyan Zhang,et al.  Global exponential stability of a class of impulsive recurrent neural networks with proportional delays via fixed point theory , 2016, J. Frankl. Inst..

[29]  Zhigang Zeng,et al.  Global asymptotical stability analysis for a kind of discrete-time recurrent neural network with discontinuous activation functions , 2016, Neurocomputing.