Uncertainty quantification in Neural Networks by Approximate Bayesian Computation: Application to fatigue in composite materials

Modern machine learning algorithms excel in a great variety of tasks, but at the same time, it is also known that those complex models need to deal with uncertainty from different sources. Consequently, understanding if the model is indeed making accurate predictions or simply guessing at random is...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Engineering applications of artificial intelligence Jg. 107; S. 104511
Hauptverfasser:	Fernández, Juan, Chiachío, Manuel, Chiachío, Juan, Muñoz, Rafael, Herrera, Francisco
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.01.2022
Schlagworte:	Approximate Bayesian Computation Bayesian Neural Network Gradient-free training Non-parametric formulation Subset Simulation Uncertainty quantification Approximate Bayesian Computation Uncertainty quantification Subset Simulation Gradient-free training Bayesian Neural Network Non-parametric formulation
ISSN:	0952-1976, 1873-6769
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!