期刊文献+

基于信度分配的串行集成CMAC及其仿真

Series Ensemble CMAC Based on Credit Assignment
下载PDF
导出
摘要 针对Albus CMAC在学习精度与存贮容量之间的矛盾,借鉴神经网络集成思想,并引入可信度的概念,提出了基于信度分配的串行集成CMAC,以提高学习系统的泛化能力和网络收敛速度。通过对复杂非线性函数的逐级降维,分步逼近,有效地提高了网络的学习精度。仿真研究进一步验证了该方案的可行性和有效性。 In order to solve the conflict between accuracy and memory capability of Albus CMAC, the ideas of neural network ensemble and credit assignment were introduced, and series ensemble CMAC based on credit assignment was proposed. The new arithmetic could effectively improve the computation accuracy. Simulation results show the feasibility and validity of the improved arithmetic by approaching complex nonlinear function step by step.
作者 鲍琼 顾幸生
出处 《华东理工大学学报(自然科学版)》 EI CAS CSCD 北大核心 2008年第5期751-754,共4页 Journal of East China University of Science and Technology
基金 国家自然科学基金项目(60774078)
关键词 CMAC 信度分配 串行 神经网络集成 CMAC credit assignment series neural network ensemble
  • 相关文献

参考文献8

  • 1Albus J S. A theory of cerebellar function[J]. Mathematical Biosciences, 1971,10 : 25-61.
  • 2刘慧,许晓鸣,张钟俊.小脑模型神经网络改进算法的研究[J].自动化学报,1997,23(4):482-488. 被引量:12
  • 3Geng Z, Haynes L S. Neural network solution for the forward kinematics problem of a stewart platform [J]. Robotics and Computer-Integrated Manufacturing, 1992, (9) : 485-495.
  • 4Carlson R, Lee C, Rothermel K. Real time neural control of an active structure[J]. International Conference on Artificial Neural Networks in Engineering, 1992, 3: 623-628.
  • 5Larsen G A, Cetinkunt S, DonmezA. CMAC neural network control for high precision motion control in the presence of large Friction [J]. Trans ASME J Dyn Syst Meas Contr, 1995,117(3) : 415-420.
  • 6于乃功,汪吉鹏.CMAC神经元网络在CSTR系统建模中的应用[J].信息与控制,1999,28(3):208-213. 被引量:4
  • 7Hansen L K, Salamon P. Neural network ensembles [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(10): 993-1001.
  • 8Shun-Feng S, Ted T, Hung T H. Credit assigned CMAC and its application to online learning robust controllers [J]. IEEE Trans on Systems, Man and Cybernetics, Part B: Cybernetics, 2003, 33(2) : 202-213.

二级参考文献8

共引文献14

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部