神经网络控制的稳定性与收敛性分析

ANALYSIS OF STABILITY AND CONVERGENCE OF NERVE-NETWORK CONTROL

摘要:本文采用梯度下降技术及非线性函数逼近理论,对神经网络控制的稳定性、收敛性进行了分析,给出稳定性和收敛性条件。最后根据本文提出的定理进行了仿真,仿真结果表明条件是正确的。

This paper is to make an analysis of the stability and convergence of nerve-network control by use of gradint descent technology and non-linear functional approxiamtion theory. And at the same time the conditions for such stability and convergence are presented also. In the end an simulation is carried out according to the theory mentioned in this essay to prove its results correct.