首页 | 本学科首页   官方微博 | 高级检索  
     

具有微分输出的神经网络New-CMAC及其学习收敛性
引用本文:王士同,J.F. Baldwin,T.P. Martin.具有微分输出的神经网络New-CMAC及其学习收敛性[J].软件学报,2001,12(5):659-667.
作者姓名:王士同  J.F. Baldwin  T.P. Martin
作者单位:1. 华东船舶工程学院计算机系;英国Bristol大学高级计算研究中心
2. 英国Bristol大学高级计算研究中心
基金项目:Supported by the National Natural Science Foundation of China under G rant No.6983004 (国家自然科学基金); British Royal Society
摘    要:基于传统的CMAC神经网络和局部加权回归技术,提出了与传统CMAC(cerebellar model articulation computer)有着同样存储空间量的改进的新CMAC网络New-CMAC,它具有传统的输出和具有其微分信息的输出,因而更适合于自动控制.接着,又提出了其新的学习算法,并研究了其学习收敛性.

关 键 词:CMAC(cerebellar  model  articulation  computer)  学习收敛  模糊泛集合  学习规则
文章编号:1000-9825/2001/12(05)0659-09
收稿时间:2000/4/18 0:00:00
修稿时间:2000年4月18日

Research on New-CMAC with Differentiability Output and Its Learning Convergence
WANG Shi tong,J.F. Baldwin and T.P. Martin.Research on New-CMAC with Differentiability Output and Its Learning Convergence[J].Journal of Software,2001,12(5):659-667.
Authors:WANG Shi tong  JF Baldwin and TP Martin
Abstract:In this paper, based on conventional CMAC (cerebellar model architecture controller) neural network and locally weighted regression, the improved New CMAC with the same amount of memory as that of conventional CMAC is presented, which has the conventional output and its derivative information output and hence is especially appropriate for automatic control. Accordingly, the new learning algorithm is investigated, and its learning convergence is proved.
Keywords:CMAC (cerebellar model architecture controller)  learning algorithm  differentiability output  locally weighted regression  
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《软件学报》浏览原始摘要信息
点击此处可从《软件学报》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