Learning convergence in the cerebellar model articulation controller

Authors:
Y. Wong;A. Sideris
Affiliations:
Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA;-
Venue:
IEEE Transactions on Neural Networks
Year:
1992

Citing 0
Cited 8

Design and analysis of direct-action CMAC PID controller

Neurocomputing
Single-input CMAC control system

Neurocomputing
Embedded support vector regression on Cerebellar Model Articulation Controller with Gaussian noise

Applied Soft Computing
ART-type CMAC network classifier

Neurocomputing
CMAC-based previous step supervisory control schemes for relaxing bound in adaptive fuzzy control

Applied Soft Computing
Pattern recognition with cerebellar model articulation controller and fractal features on partial discharges

Expert Systems with Applications: An International Journal
An efficient CMAC neural network for stock index forecasting

Expert Systems with Applications: An International Journal
Sales forecasting for computer wholesalers: A comparison of multivariate adaptive regression splines and artificial neural networks

Decision Support Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

A new way to look at the learning algorithm in the cerebellar model articulation controller (CMAC) proposed by J.S. Albus (1975) is presented. A proof that the CMAC learning always converges with arbitrary accuracy on any set of training data is obtained. An alternative way to implement CMAC based on the insights obtained in the process is proposed. The scheme is tested with a computer simulation for learning the inverse dynamics of a two-link robot arm