Neural networks with robust backpropagation learning algorithm

A robust error suppressor function, which is independent of the underlying probability density function and convenient for computer programs, is proposed to robustify the backpropagation learning algorithm of multilayer feedforward networks. Its performance is studied for simulated data sets.

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Analytica chimica acta Jg. 322; H. 1; S. 21 - 29
1. Verfasser:	Walczak, B.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Amsterdam Elsevier B.V 1996 Elsevier
Schlagworte:	Analytical chemistry Chemistry Chemometrics Exact sciences and technology General, instrumentation Neural networks Robust backpropagation learning algorithm Neural networks Robust backpropagation learning algorithm Chemometrics Learning Multiple layer Robustness Neural network Feedforward Algorithm
ISSN:	0003-2670, 1873-4324
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!