Stochastic Stability Analysis of Delayed Hopfield Neural Networks with Impulse Effects

This paper studies the global exponential stability of the delayed Hopfield neural networks with both stochastic perturbations and impulse effects. By means of the Ito formula, Lyapunov-Razumikhin theorems and certain inequality techniques, some sufficient criteria are obtained which guarantee the global exponential stability of the delayed Hopfield neural networks with stochastic perturbations and impulse effects. The results characterize the intricate effects of the impulses and then can be used to estimate the feasible upper bounds of impulses. Furthermore, a numerical simulation is given to illustrate the validity of our results.

[1]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Jinde Cao,et al.  Stability and Hopf Bifurcation in a Simplified BAM Neural Network With Two Time Delays , 2007, IEEE Transactions on Neural Networks.

[3]  X. Mao,et al.  Razumikhin-type theorems on exponential stability of stochastic functional differential equations , 1996 .

[4]  Hui-Ran Jia,et al.  Robust stability for stochastic interval Hopfield neural networks with time delays , 2010, 2010 Sixth International Conference on Natural Computation.

[5]  L. Berezansky,et al.  Exponential Stability of Linear Delay Impulsive Differential Equations , 1993 .

[6]  Chuang Zhang,et al.  Thermal Compensation Method for CMOS Digital Integrated Circuits Using Temperature-Adaptive DC–DC Converter , 2006, IEEE Transactions on Circuits and Systems II: Express Briefs.

[7]  Chuandong Li,et al.  Stabilizing Effects of Impulses in Delayed BAM Neural Networks , 2008, IEEE Transactions on Circuits and Systems II: Express Briefs.

[8]  Masahiko Morita,et al.  Capacity of associative memory using a nonmonotonic neuron model , 1993, Neural Networks.

[9]  Zhihao Yang,et al.  Razumikhin-type Theorems on Exponential Stability of Stochastic Functional Differential Equations with Infinite Delay , 2010 .

[10]  Cong Wang,et al.  Deterministic Learning and Rapid Dynamical Pattern Recognition , 2007, IEEE Transactions on Neural Networks.

[11]  Masahiko Morita,et al.  Associative memory with nonmonotone dynamics , 1993, Neural Networks.

[12]  Shouming Zhong,et al.  Robust stability analysis for discrete-time stochastic neural networks systems with time-varying delays , 2009, Appl. Math. Comput..

[13]  Wei Feng,et al.  Robust stability analysis of uncertain stochastic neural networks with interval time-varying delay , 2009 .

[14]  Guy M. Wallis,et al.  Stability criteria for unsupervised temporal association networks , 2005, IEEE Transactions on Neural Networks.

[15]  Xinzhi Liu,et al.  Impulsive Stabilization of High-Order Hopfield-Type Neural Networks With Time-Varying Delays , 2008, IEEE Transactions on Neural Networks.

[16]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Xinzhi Liu,et al.  The method of Lyapunov functionals and exponential stability of impulsive systems with time delay , 2007 .