The learning convergence of CMAC in frequency domain and a modified algorithm

Author

Lei, Zhang ; Qi-xin, Cao

Author_Institution

Res. Inst. of Robot., Shanghai Jiao Tong Univ., Shanghai

fYear

2008

fDate

25-27 June 2008

Firstpage

6212

Lastpage

6216

Abstract

The analysis on the learning convergence of CMAC in frequency domain is firstly extended to a more general case where the training samples are evenly distributed in the quantitative range and the learning rate is other than one. The convergence condition is presented and the influence of the learning rate beta on the convergence range is analyzed. If 0< beta<1, CMAC is convergent in the whole frequency domain. If 1lesbeta<2, the convergence of CMAC will become more unstable with beta becoming larger. To overcome this problem, a modified algorithm is proposed and simulation results prove the stability of CMAC can be improved significantly.

Keywords

cerebellar model arithmetic computers; frequency-domain analysis; learning (artificial intelligence); CMAC; frequency domain; learning convergence; Algorithm design and analysis; Convergence; Frequency domain analysis; Intelligent control; Intelligent robots; Robotics and automation; Stability; CMAC; frequency domain; learning convergence;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on

Conference_Location

Chongqing

Print_ISBN

978-1-4244-2113-8

Electronic_ISBN

978-1-4244-2114-5

Type

conf

DOI

10.1109/WCICA.2008.4592801

Filename

4592801