Comparison of Optimized Backpropagation Algorithms

Comparison of Optimized Backpropagation Algorithms (1993)

Cached

Download Links

[www.uni-koblenz.de]

by W. Schiffmann , M. Joost , R. Werner

Venue:	Proc. of ESANN'93, Brussels
Citations:	36 - 1 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Comparison of Optimized Backpropagation Algorithms	user correction - Legacy Corrections
AUTHOR NAME	W. Schiffmann	SVM HeaderParse 0.1
AUTHOR AFFIL	University of Koblenz; Institute of Physics	SVM HeaderParse 0.2
AUTHOR ADDR	Rheinau 3--4; W-5400 Koblenz	SVM HeaderParse 0.1
AUTHOR NAME	M. Joost	SVM HeaderParse 0.1
AUTHOR NAME	R. Werner	SVM HeaderParse 0.1
AUTHOR AFFIL	University of Koblenz; Institute of Physics	SVM HeaderParse 0.2
AUTHOR ADDR	Rheinau 3--4; W-5400 Koblenz	SVM HeaderParse 0.1
ABSTRACT	Backpropagation is one of the most famous training algorithms for multilayer perceptrons. Unfortunately it can be very slow for practical applications. Over the last years many improvement strategies have been developed to speed up backpropagation. It's very difficult to compare these different techniques, because most of them have been tested on various specific data sets. Most of the reported results are based on some kind of tiny and artificial training sets like XOR, encoder or decoder. It's very doubtful if these results hold for more complicate practical application. In this report an overview of many different speedup techniques is given. All of them were assessed by a very hard practical classification task, which consists of a big medical data set. As you will see many of these optimized algorithms fail in learning the data set. 1 Introduction This report is intended to summarize our experience using many different speedup techniques for the backpropagation algorithm. We have...	user correction - Legacy Corrections
YEAR	1993	INFERENCE
VENUE	Proc. of ESANN'93, Brussels	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	97--104	INFERENCE
CITATIONS	18 found	ParsCit 1.0