Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
REVIEW OF BAYESIAN NEURAL NETWORKS WITH AN APPLICATION TO NEAR-INFRARED SPECTROSCOPY
Autore:
THODBERG HH;
Indirizzi:
DANISH MEAT RES INST,MAGLEGAARDSVEJ 2 DK-4000 ROSKILDE DENMARK
Titolo Testata:
IEEE transactions on neural networks
fascicolo: 1, volume: 7, anno: 1996,
pagine: 56 - 72
SICI:
1045-9227(1996)7:1<56:ROBNNW>2.0.ZU;2-8
Fonte:
ISI
Lingua:
ENG
Soggetto:
FRAMEWORK;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
CompuMath Citation Index
Science Citation Index Expanded
Science Citation Index Expanded
Science Citation Index Expanded
Science Citation Index Expanded
Citazioni:
25
Recensione:
Indirizzi per estratti:
Citazione:
H.H. Thodberg, "REVIEW OF BAYESIAN NEURAL NETWORKS WITH AN APPLICATION TO NEAR-INFRARED SPECTROSCOPY", IEEE transactions on neural networks, 7(1), 1996, pp. 56-72

Abstract

MacKay's Bayesian framework for backpropagation is a practical and powerful means to improve the generalization ability of neural networks,It is based on a Gaussian approximation to the posterior weight distribution, The framework is extended, reviewed, and demonstrated in a pedagogical way, The notation Is simplified using the ordinary weight decay parameter, and a detailed and explicit procedure for adjusting several weight decay parameters is given, Bayesian backprop is applied inthe prediction of fat content in minced meat from near infrared spectra, It out performs ''early stopping'' as well as quadratic regression, The evidence of a committee of differently trained networks is computed, and the corresponding improved generalization is verified, The error bars on the predictions of the fat content are computed. There arethree contributors: The random noise, the uncertainty in the weights,and the deviation among the committee members, The Bayesian frameworkis compared to Moody's GPE. Finally, MacKay and Neal's automatic relevance determination, in which the weight decay parameters depend on the input number, is applied to the data with improved results.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 27/11/20 alle ore 13:52:15