论文部分内容阅读
选用正态函数作为模糊变量的隶属函数 ,给出了基于Takagi_Sugeno模型的模糊神经网络的用于学习的性能指标 ,并对其性质进行了分析 .在此基础上将二阶段变半径随机搜索法用作模糊神经网络的学习算法 .这种方法简便易行 ,可使模糊神经网络达到较高的精度 .该文给出了神经网络记忆容量的定义并求出了基于TS模型的模糊神经网络的记忆容量 .
The normal function is chosen as the membership function of fuzzy variables, and the performance index for learning based on Takagi_Sugeno model is given and its properties are analyzed.On this basis, the two-stage variable radius random search method is used As fuzzy neural network learning algorithm.This method is simple and easy, can make the fuzzy neural network to achieve high accuracy.This paper gives the definition of neural network memory capacity and obtains the fuzzy neural network memory based on the TS model Capacity.