CMAC neural networks structures

Author

Mohajeri, Kamran ; Pishehvar, Ghasem ; Seifi, Mohammad

Author_Institution

North Power Transm. Maintenance Co., Sari, Iran

fYear

2009

Firstpage

39

Lastpage

45

Abstract

Cerebellar Model Articulation Controller (CMAC) NN is a computational model of cerebellum introduced as an alternative to backpropagated multilayer networks to control robot arms. From then it has seen many improvements and has been applied in many other areas as a general NN. These improvements have been in the context of generalization, learning techniques, differentiability, memory size, fuzzification and hardware implementation. This paper is a systematic review of CMAC´s different structures and applications.

Keywords

fuzzy set theory; manipulators; neural nets; CMAC neural networks structures; cerebellar model articulation controller; computational model; control robot arms; differentiability; fuzzification; hardware implementation; learning techniques; memory size; multilayer networks; Brain modeling; Computer networks; Function approximation; Hardware; Hypercubes; Least squares approximation; Multi-layer neural network; Multilayer perceptrons; Neural networks; Robot control;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence in Robotics and Automation (CIRA), 2009 IEEE International Symposium on

Conference_Location

Daejeon

Print_ISBN

978-1-4244-4808-1

Electronic_ISBN

978-1-4244-4809-8

Type

conf

DOI

10.1109/CIRA.2009.5423175

Filename

5423175