A hybrid maximum error algorithm with neighborhood training for CMAC

Author

Sayil, Selabattin ; Lee, Kwang Y.

Author_Institution

Dept. of Electr. Eng., Pamukkale Univ., Kinikli-Denizli, Turkey

Volume

1

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

165

Lastpage

170

Abstract

Several possible algorithms and training methods for the CMAC network are analyzed thoroughly. Improvements are then examined and a hybrid approach has been developed for the maximum error algorithm by using the neighborhood training technique for the initial training period. The employment of the technique yielded faster initial convergence which is very important for many control applications. The proposed hybrid approach is demonstrated on an inverse kinematics problem of a two-link robot arm

Keywords

cerebellar model arithmetic computers; learning (artificial intelligence); neurocontrollers; position control; robot kinematics; CMAC; hybrid approach; hybrid maximum error algorithm; initial convergence; inverse kinematics; maximum error algorithm; neighborhood training; training methods; two-link robot arm; Algorithm design and analysis; Brain modeling; Convergence; Employment; Information processing; Iterative algorithms; Kinematics; Mathematical model; Neural networks; Robots;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1005463

Filename

1005463