依赖时延BAM神经网络的全局吸引性分析

DELAY-DEPENDENT GLOBAL ATTRACTIVITY IN BAM NEURAL NETWORKS

由于神经网络模型具有光滑单调激活函数 (如 sigmoid函数 ) ,因此利用单调动力学理论得到了判定时延BAM模型的全局吸引性的准则 ,这个准则是与时延的大小有关的 ,并证明了自抑制联结可产生全局收敛性 ,给出了一个数值例子以说明所得结论的正确性 .

In the case of monotone and smooth activation functional, the theory of monotone dynamical systems is applied to obtain criteria for global attractivity of the BAM with time delay. Such criteria depend on the magnitude of delays and show that self inhibitory connection can contribute to the global convergence. A numerical example is given to illustrate the correctness of the results obtained.