Confidence estimation methods for neural networks: a practical comparison

Feedforward neural networks, particularly multilayer perceptrons, are widely used in regression and classification tasks. A reliable and practical measure of prediction confidence is essential. In this work three alternative approaches to prediction confidence estimation are presented and compared....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2001-11, Vol.12 (6), p.1278-1287
Hauptverfasser:	Papadopoulos, G., Edwards, P.J., Murray, A.F.
Format:	Artikel
Sprache:	eng
Schlagworte:	Bayesian analysis Bayesian methods Confidence Feedforward neural networks Industrial control Maximum likelihood estimation Multi-layer neural network Multilayer perceptrons Neural networks Predictive models Probability Studies Testing
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!