Stability analysis of neural networks with periodic coefficients and piecewise constant arguments

Abstract Global exponential stability of a class of neural networks with periodic coefficients and piecewise constant arguments is investigated in this paper. A new definition of exponential stability and a novel differential inequality with piecewise constant arguments are introduced to obtain sufficient conditions for the globally exponential stability of the periodic solution of neural networks. The stability criteria are independent on the upper bound of the adjacent element difference of the discontinuous switching moments. According to the new definition of exponential stability and the novel differential inequality, not only it is not necessary to establish any relationship between the norms of the states with/without piecewise constant arguments, but also the stability criteria for the neural networks can be obtained just in terms of the original differential equation, rather than the equivalent integral equation which is widely used in the early works. Typical numerical examples are utilized to illustrate the validity and improvement in less conservatism of the theoretical results.

[1]  Huaguang Zhang,et al.  Novel Weighting-Delay-Based Stability Criteria for Recurrent Neural Networks With Time-Varying Delay , 2010, IEEE Transactions on Neural Networks.

[2]  Marat Akhmet,et al.  On periodic solutions of differential equations with piecewise constant argument , 2008, Comput. Math. Appl..

[3]  Enes Yilmaz,et al.  Global exponential stability of neural networks with non-smooth and impact activations , 2011, Neural Networks.

[4]  Daoyi Xu,et al.  Stability Analysis and Design of Impulsive Control Systems With Time Delay , 2007, IEEE Transactions on Automatic Control.

[5]  A Hjelmfelt,et al.  Pattern recognition, chaos, and multiplicity in neural networks of excitable systems. , 1994, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Enes Yilmaz,et al.  Stability in cellular neural networks with a piecewise constant argument , 2010, J. Comput. Appl. Math..

[7]  Jurang Yan,et al.  Necessary and sufficient condition for the global attractivity of the trivial solution of a delay equation with continuous and piecewise constant arguments , 1997 .

[8]  Jinde Cao,et al.  Globally exponential stability conditions for cellular neural networks with time-varying delays , 2002, Appl. Math. Comput..

[9]  Georgi M. Dimirovski,et al.  New delay-dependent stability criteria for recurrent neural networks with time-varying delays , 2008, Neurocomputing.

[10]  Jinde Cao,et al.  Periodic bidirectional associative memory neural networks with distributed delays , 2006 .

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

[12]  Marat Akhmet,et al.  Nonlinear Hybrid Continuous/Discrete-Time Models , 2011 .

[13]  İlhan Öztürk,et al.  Stability analysis of a population model with piecewise constant arguments , 2011 .

[14]  Wei Xing Zheng,et al.  Novel stability of cellular neural networks with interval time-varying delay , 2008, Neural Networks.

[15]  邓飞其,et al.  “Time Delays and Stimulus-Dependent Pattern Formation in Periodic Environments in Isolated Neurons’’的注记 , 2005 .

[16]  Kenneth L. Cooke,et al.  Oscillations in systems of differential equations with piecewise constant argument , 1989 .

[17]  Enes Yilmaz,et al.  Method of Lyapunov functions for differential equations with piecewise constant delay , 2011, J. Comput. Appl. Math..

[18]  S. Coombes,et al.  Delays in activity-based neural networks , 2009, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[19]  W. Freeman.  The physiology of perception. , 1991, Scientific American.

[20]  Jun Wang,et al.  Algebraic criteria for global exponential stability of cellular neural networks with multiple time delays , 2003 .

[21]  Xinzhi Liu,et al.  Comparison principle and stability of differential equations with piecewise constant arguments , 2013, J. Frankl. Inst..

[22]  V. Lakshmikantham,et al.  Excitability of a second-order delay differential equation , 1999 .

[23]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[24]  Anatoli F. Ivanov.  Global dynamics of a differential equation with piecewise constant argument , 2009 .

[25]  Tamás Roska,et al.  Cellular neural networks with nonlinear and delay-type template elements , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[26]  Marat Akhmet,et al.  Integral manifolds of differential equations with piecewise constant argument of generalized type , 2005 .

[27]  Enes Yilmaz,et al.  Stability analysis of recurrent neural networks with piecewise constant argument of generalized type , 2010, Neural Networks.

[28]  Senol Kartal,et al.  Stability and bifurcation analysis of a mathematical model for tumor–immune interaction with piecewise constant arguments of delay , 2014 .

[29]  Nikita Barabanov,et al.  Stability analysis of discrete-time recurrent neural networks , 2002, IEEE Trans. Neural Networks.

[30]  Xiaoai Li.  Existence and Exponential Stability of Solutions for Stochastic Cellular Neural Networks with Piecewise Constant Argument , 2014, J. Appl. Math..

[31]  I Oztürk,et al.  Stability analysis of a mathematical model in a microcosm with piecewise constant arguments. , 2012, Mathematical biosciences.

[32]  W. Freeman,et al.  How brains make chaos in order to make sense of the world , 1987, Behavioral and Brain Sciences.

[33]  Zhigang Zeng,et al.  Robust stability analysis of interval fuzzy Cohen-Grossberg neural networks with piecewise constant argument of generalized type , 2012, Neural Networks.

[34]  E. Glaeser,et al.  Inequality , 1998, Encyclopedia of the UN Sustainable Development Goals.

[35]  Kenneth L. Cooke,et al.  Retarded differential equations with piecewise constant delays , 1984 .

[36]  J. Hopfield.  Neurons withgraded response havecollective computational properties likethoseoftwo-state neurons , 1984 .

[37]  Stavros Busenberg,et al.  MODELS OF VERTICALLY TRANSMITTED DISEASES WITH SEQUENTIAL-CONTINUOUS DYNAMICS , 1982 .

[38]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[39]  Jinde Cao,et al.  Periodic solutions and its exponential stability of reaction–diffusion recurrent neural networks with continuously distributed delays , 2006 .

[40]  Marat Akhmet,et al.  Impulsive Hopfield-type neural network system with piecewise constant argument , 2010 .

[41]  Kuo-Shou Chiu.  Stability of oscillatory solutions of differential equations with a general piecewise constant argument. , 2011 .

[42]  J. E. Moreira.  Intermittency in a neural network with variable threshold , 1993 .

[43]  Gen-Qiang Wang,et al.  Periodic solutions of a neutral differential equation with piecewise constant arguments , 2007 .

[44]  Lihong Huang,et al.  Periodic oscillation for a class of neural networks with variable coefficients , 2005 .

[45]  S. Shah,et al.  ADVANCED DIFFERENTIAL EQUATIONS WITH PIECEWISE CONSTANT ARGUMENT DEVIATIONS , 1983 .

[46]  Joseph Wiener,et al.  Generalized Solutions of Functional Differential Equations , 1993 .

[47]  Marat Akhmet,et al.  Stability of differential equations with piecewise constant arguments of generalized type , 2008 .

[48]  Ju H. Park,et al.  Stability for Neural Networks With Time-Varying Delays via Some New Approaches , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[49]  Zhi-Hong Guan,et al.  On impulsive autoassociative neural networks , 2000, Neural Networks.

[50]  Kondalsamy Gopalsamy,et al.  Persistence and Global Stability in a Population Model , 1998 .