Improved conditions for global exponential stability of recurrent neural networks with time-varying delays
Improved conditions for global exponential stability of recurrent neural networks with time-varying delays
复制标题
DOI：
10.1109/tnn.2006.873283
复制
发表时间：
2006-05
影响因子：
--
通讯作者：
Z. Zeng;Jun Wang
中科院分区：
文献类型：
--
作者：
Z. Zeng;Jun Wang
本文给出了具有有界激活函数和变时滞的递归神经网络全局指数稳定性的新的理论结果。稳定性条件依赖于外部输入，连接权，和时间延迟的递归神经网络。利用这些结果，可以得到递归神经网络的全局指数稳定性，以及平衡点的估计位置。作为典型的代表，Hopfield神经网络（HNN）和细胞神经网络（CNN）进行了详细的研究
This paper presents new theoretical results on global exponential stability of recurrent neural networks with bounded activation functions and time-varying delays. The stability conditions depend on external inputs, connection weights, and time delays of recurrent neural networks. Using these results, the global exponential stability of recurrent neural networks can be derived, and the estimated location of the equilibrium point can be obtained. As typical representatives, the Hopfield neural network (HNN) and the cellular neural network (CNN) are examined in detail