###
DOI:
Journal of Software:2001.12(5):659-667

具有微分输出的神经网络New-CMAC及其学习收敛性
王士同,J.F.Baldwin,T.P.Martin
(华东船舶工程学院计算机系,江苏镇江 212003;英国Bristol大学高级计算研究中心,英国)
Research on New-CMAC with Differentiability Output and Its Learning Convergence
WANG Shi tong,J.F. Baldwin,T.P. Martin
()
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 2583   Download 2454
Received:April 18, 2000    Revised:October 17, 2000
> 中文摘要: 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.
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.
文章编号:     中图分类号:    文献标志码:
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 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
Foundation items:
Reference text:

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.软件学报,2001,12(5):659-667

WANG Shi tong,J.F. Baldwin,T.P. Martin.Research on New-CMAC with Differentiability Output and Its Learning Convergence.Journal of Software,2001,12(5):659-667