Prediction intervals for Deep Neural Networks

The aim of this paper is to propose a suitable method for constructing prediction intervals for the output of neural network models. To do this, we adapt the extremely randomized trees method originally developed for random forests to construct ensembles of neural networks. The extra-randomness intr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-05
Hauptverfasser:	Mancini, Tullio, Calvo-Pardo, Hector, Olmo, Jose
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Decision trees Forest management Intervals Monte Carlo simulation Neural networks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!