DocumentCode :
280295
Title :
Neural learning algorithms: some empirical trials
Author :
Forsyth, Richard
Author_Institution :
Dept. of Psychol., Nottingham Univ., UK
fYear :
1990
fDate :
33052
Firstpage :
42583
Lastpage :
42589
Abstract :
Reports some empirical trials comparing seven different neural learning algorithms (including two versions of back propagation) on four test problems. Though limited in scope the study does shed light on the performance of a variety of learning techniques, compared under relatively uniform conditions. The results cast some doubt on the status of back propagation as an `industrial strength´ learning algorithm
Keywords :
learning systems; neural nets; pattern recognition; back propagation; genetic algorithms; machine learning; neural computing; neural learning algorithms; pattern recognition;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Machine Learning, IEE Colloquium on
Conference_Location :
London
Type :
conf
Filename :
190516
Link To Document :
بازگشت