时滞recurrent神经网络模型的全局渐近稳定性

Over-all Exponential Stability of Recurrent Neural Networks with Time-varying Delay

讨论了时滞recurrent神经网络模型的全局渐近稳定性,通过构造适当的Lyapuov函数,利用线性矩阵不等式,给出了一类常时滞recurrent神经网络的新的充分条件,所获的稳定性条件是时滞相关的,稳定性判别条件更宽松.最后通过一个实例说明方法的可行性.

The over-all asymptotic stability of recurrent neural networks is discussed in this paper. A new sufficient condition for the asymptotic stability is presented. This condition is dependent on the size of delays and provides more space for stability judgment. A practical example is given to illustrate the applicability of this condition.