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.

Uložené v:

Podrobná bibliografia
Vydané v:	Analytica chimica acta Ročník 322; číslo 1; s. 21 - 29
Hlavný autor:	Walczak, B.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Amsterdam Elsevier B.V 1996 Elsevier
Predmet:	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
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	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.
ISSN:	0003-2670 1873-4324
DOI:	10.1016/0003-2670(95)00552-8