一类具离散时变时滞和分布时滞神经网络的指数稳定性(英文)

Exponential Stability of a Class of Neural Networks with Discrete Time-varying and Distributed Delays

本文讨论一类具离散时变时滞和分布时滞神经网络的指数稳定性。利用非线性测度,本文得到一个与时滞无关的充分条件,它保证了平衡点的存在性、唯一性和指数稳定性。既然新稳定准则不要求激活函数的有界性、单调性及可微性和随时间改变的传递延迟函数的可微性,那么它是某些已有结果的推广。此外,本文的方法的另一个优点是给出了解的指数收敛速度。最后,给出的例子说明我们的方法是有效的。

The paper is devoted to the exponential stability of a class of neural networks with both discrete time-varying and distributed delays. In virtue of nonlinear measure, a delay- independent suffcient condition is derived for the existence, uniqueness and exponential stability of the equilibrium point. Since assumptions on boundedness, monotonicity and di？erentiability of activation functions and differentiability of time-varying transmission delay functions are avoided, the new stability criterion is an extension of some existing results. Moreover, an additional merit of the method is to provide the exponentially con- vergent velocity of the solutions. Finally, an example is provided to illustrate effectiveness of the method.