具有微分输出的神经网络New-CMAC及其学习收敛性(英文)  

Research on New-CMAC with Differentiability Output and Its Learning Convergence

作　　者：王士同 J.F.Baldwin T.P.Martin2 

机构地区：[1]华东船舶工程学院计算机系,江苏镇江212003 [2]英国Bristol大学高级计算研究中心

出　　处：《软件学报》2001年第5期666-667,共2页Journal of Software

基　　金：国家自然科学基金No.6 98 30 0 4&&

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 com-puter)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 .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.

关 键 词：模糊泛集合 学习规则 学习收敛性 神经网络 微分输出 New-CMAC 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]