Logarithmic Stability of Neural Networks with Time-Varying Delay

Ojha, A.K.; Mallick, D.
December 2007
International Journal of Computational & Applied Mathematics;2007, Vol. 2 Issue 3, p209
Academic Journal
Convergence and stability are important features of neural network. It has been observed that the neural network leads to instability with time-vary delays. In this present paper we have made an attempt to establish the stability of neural network by considering logarithmic approach, where the activation function is assumed to be globally lipschitz continous. The sufficient condition ensuring the delayed neural network for attaining unique equilibrium point which is globally stable, has been proved by using linear matrix inequality approach (LMI).


Related Articles

  • Global Exponential Stability of Periodic Oscillation for Nonautonomous BAM Neural Networks with Distributed Delay. Yi Wang; Zhongjun Ma; Hongli Liu // Journal of Inequalities & Applications;2009, Vol. 2009, p1 

    We derive a new criterion for checking the global stability of periodic oscillation of bidirectional associative memory (BAM) neural networks with periodic coefficients and distributed delay, and find that the criterion relies on the Lipschitz constants of the signal transmission functions,...

  • Global Asymptotical Stability of Delayed Impulsive Neural Networks without Lipschitz Neuron Activations. Ailong Wu; Jine Zhang; Chaojin Fu // European Journal of Pure & Applied Mathematics;2010, Vol. 3 Issue 5, p806 

    In this paper, based on the homeomorphism theory and Lyapunov functional method, we investigate global asymptotical stability for a novel class of delayed impulsive neural networks without Lipschitz neuron activations. Some sufficient conditions are derived which ensure the existence,...

  • Stability and convergence of an implicit numerical method for the non-linear fractional reaction�subdiffusion process. ZHUANG, P.; LIU, F.; ANH, V.; TURNER, I. // IMA Journal of Applied Mathematics;Oct2009, Vol. 74 Issue 5, p645 

    In this paper, we consider the following non-linear fractional reaction�subdiffusion process (NFR-SubDP):where f(u, x, t) is a linear function of u, the function g(u, x, t) satisfies the Lipschitz condition and 0Dt1�? is the Riemann�Liouville time fractional partial derivative of...

  • A neural network model for stroboscopic alternative motion. Carmesin, Hans-Otto; Arndt, Stefan // Biological Cybernetics;1996, Vol. 75 Issue 3, p239 

    .A neural network which models multistable perception is presented. The network consists of sensor and inner neurons. The dynamics is established by a stochastic neuronal dynamics, a formal Hebb-type coupling dynamics and a resource mechanism that corresponds to saturation effects in perception....

  • On delay-dependent stability for a class of nonlinear stochastic delay-differential equations. Rodkina, Alexandra; Basin, Michael // Mathematics of Control, Signals & Systems;Jun2006, Vol. 18 Issue 2, p187 

    Global asymptotic stability conditions for nonlinear stochastic systems with state delay are obtained based on the convergence theorem for semimartingale inequalities, without assuming the Lipschitz conditions for nonlinear drift functions. The Lyapunov�Krasovskii and degenerate functionals...

  • Convergent families of approximate inertial manifolds for nonautonomous evolution equations. Zongxing, Wang; Xianling, Fan; Zhengyou, Zhu // Applied Mathematics & Mechanics;Aug1998, Vol. 19 Issue 8, p765 

    In this paper, the long time behavior of nonautonomous infinite dimensional dynamical systems is studied. A family of convergent approximate inertial manifolds for a class of evolution equations has been constructed when the spectral gap condition is satisfied.

  • Statistical Approximation Properties of a Generalization of Positive Linear Operators. Canatan, Reyhan; Doğru, Ogün // European Journal of Pure & Applied Mathematics;2012, Vol. 5 Issue 1, p75 

    In the present paper, we introduce a generalization of positive linear operators and obtain its Korovkin type statistical approximation properties. The rates of statistical convergence of this generalization is also obtained by means of modulus of continuity and Lipschitz type maximal functions....

  • MEAN SQUARE CONVERGENCE OF STOCHASTIC ?-METHODS FOR NONLINEAR NEUTRAL STOCHASTIC DIFFERENTIAL DELAY EQUATIONS. Siqing Gan; Schurz, Henri; Haomin Zhang // International Journal of Numerical Analysis & Modeling;2011, Vol. 8 Issue 2, p201 

    This paper is devoted to the convergence analysis of stochastic ?-methods for nonlinear neutral stochastic differential delay equations (NSDDEs) in It� sense. The basic idea is to reformulate the original problem eliminating the dependence on the differentiation of the solution in the past...

  • Convergence of inexact difference methods under the generalized Lipschitz conditions. Shakhno, S. // Journal of Mathematical Sciences;Dec2010, Vol. 171 Issue 4, p453 

    We study the convergence of the inexact chord method and Steffensen method for the solution of systems of nonlinear equations under the generalized Lipschitz conditions for first-order divided differences. We consider methods with a check of the relative discrepancy. The results obtained easily...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics