EFNN——一种增强型模糊神经网络  

An enforced fuzzy neural networks

作　　者：陈保国[1] 朱奕[1] 张华[1] 张家余[1] 

机构地区：[1]哈尔滨工业大学控制工程系,黑龙江哈尔滨150001

出　　处：《哈尔滨工业大学学报》2001年第1期89-92,共4页Journal of Harbin Institute of Technology

摘　　要：提出了一种较为广义的增强型模糊神经网络 ,以达到更高的非线性系统逼近能力 .该网络模糊规则的结论以函数形式给出 ,从而决定了网络的结构由两个子网络组成 ,即特征网络和功能网络 .网络采用梯度算法来修正网络的参数 .仿真表明 :该网络具有较强的非线性逼近能力和较快的学习速度 .Presents the general enforced fuzzy neural network (EFNN) proposed to obtain higher accuracy of closing in on nonlinear system with the consequent fuzzy rules given in the form of function, which determines that the structure of network is a combination of two sub networks. Character network and function one, and the parameters are tuned with the grade descending algorithms and concludes from simulation results that the network has a higher accuracy of closing in on nonlinear system and a faster training speed.

关 键 词：特征网络 功能网络 增强型模型神经网络 梯度算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]