首页 | 本学科首页   官方微博 | 高级检索  
     

一种模糊CMAC神经网络
引用本文:邓志东,孙增圻,张再兴.一种模糊CMAC神经网络[J].自动化学报,1995,21(3):288-294.
作者姓名:邓志东  孙增圻  张再兴
作者单位:1.清华大学计算机系智能技术与系统国家重点实验室,北京
摘    要:提出了一种模糊CMAC(小脑模型关节控制器)神经网络,它由输入层、模糊化层、模糊相 联层、模糊后相联层与输出层等5层节点组成,具有与CMAC相似的单层连接权,可通过BP 算法学习推论参数或模糊规则.给出了网络的连接结构与学习算法,并将其应用于函数逼近 问题中仿真结果验证了该方法较之CMAC的优越性.

关 键 词:神经网络    模糊逻辑    CMAC    函数逼近
收稿时间:1993-12-23

A Fuzzy CMAC Neural Network
Deng Zhidong,Sun Zengqi,Zhang Zaixing.A Fuzzy CMAC Neural Network[J].Acta Automatica Sinica,1995,21(3):288-294.
Authors:Deng Zhidong  Sun Zengqi  Zhang Zaixing
Affiliation:1.Dept of Computer Sci&Tech,Tsinghua University Beijing
Abstract:In this paper a fuzzy CMAC neural network is proposed, which is composed of input layer. fuzzified layer, fuzzy association layer, and output laver. It has the similiar single layer link weights to GMAC and updates the consequence parameters of Takagi's fuzzy reasoning through BP algorithms. foe proposed fuzzy-neural structure is described and the supervised learning algorithm is derived. The simulation results with a function approximation problem problem are shown that the proposed scheme is superior to CMAC in many aspects.
Keywords:Neural network  fuzzy logic  CMAC  function approximation  
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号