Fuzzy Control of Back-Propagation Training
Michael Negnevitsky and Martin J. Ringrose
School of Engineering, University of Tasmania,
GPO Box 252-65 Hobart, Tasmania 7001 Australia
A fuzzy logic controller for updating training parameters in the error back-propagation algorithm is presented. The controller is based on heuristic rules for speeding up the convergence of training process, incorporating both learning rate and momentum constant changes.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 International License.