Generalizing CMAC architecture and training

Author

González-Serrano, Francisco J. ; Figueiras-Vidal, Anibal R. ; Artés-Rodriguez, Antonio

Author_Institution

ETSI Telecomunicacion, Vigo Univ., Spain

Volume

9

Issue

6

fYear

1998

fDate

11/1/1998 12:00:00 AM

Firstpage

1509

Lastpage

1514

Abstract

The cerebellar model articulation controller (CMAC) is a simple and fast neural-network based on local approximations. However, its rigid structure reduces its accuracy of approximation and speed of convergence with heterogeneous inputs. In this paper, we propose a generalized CMAC (GCMAC) network that considers different degrees of generalization for each input. Its representation abilities are analyzed, and a set of local relationships that the output function must satisfy are derived. An adaptive growing method of the network is also presented. The validity of our approach and methods are shown by some simulated examples

Keywords

cerebellar model arithmetic computers; convergence; generalisation (artificial intelligence); learning (artificial intelligence); neural net architecture; CMAC architecture; CMAC training; GCMAC; adaptive growing method; cerebellar model articulation controller; convergence speed; generalized CMAC; heterogeneous inputs; local approximations; Approximation methods; Computational modeling; Computer architecture; Computer networks; Convergence; Digital arithmetic; Function approximation; Neural networks; Table lookup; Telecommunications;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.728400

Filename

728400