Paper available

[Martin Riedmiller]

The following paper is available via anonymous ftp from i11s16.ira.uka.de.
Instructions for retrieval follow the abstract.

*****************************************************************

	Advanced Supervised Learning in Multi-layer Perceptrons -	
	From Backpropagation to Adaptive Learning Algorithms

		Martin Riedmiller

		Institut fuer Logik, Komplexitaet 
		und Deduktionssyteme 
 	        University of Karlsruhe		
      		W-76128 Karlsruhe
      		FRG
      		riedml at ira.uka.de


		ABSTRACT

Since the presentation of the backpropagation algorithm a vast variety
of improvements of the technique for training the weights in a
feed-forward neural network have been proposed.  The following article
introduces the concept of supervised learning in multi-layer
perceptrons based on the technique of gradient descent.  Some problems
and drawbacks of the original backpropagation learning procedure are
discussed, eventually leading to the development of more sophisticated
techniques.

This article concentrates on adaptive learning strategies. Some of
the most popular learning algorithms are described and discussed
according to their classification in terms of global and local
adaptation strategies.

The behavior of several learning procedures on some popular benchmark
problems is reported, thereby illuminating convergence, robustness,
and scaling properties of the respective algorithms.



This paper has been accepted for publication in the special issue on Neural
Network Standards of  "Computer Standards & Interfaces", volume 16,  edited
by J. Fulcher.  Elsevier Science Publishers, Amsterdam, 1994.

*****************************************************************

                     ------------------------------

To obtain a copy of this paper, please follow the following FTP instructions:

ftp i11s16.ira.uka.de (or ftp 129.13.33.16)
Name: anonymous
Password: (your email address)
ftp> cd pub/neuro/papers
ftp> binary
ftp> get riedml.csi94.ps.Z
ftp> quit
% uncompress <>.ps.Z
% lpr <>.ps