Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal distribution or other distribution encouraging sparsity. However, this...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-10
Hauptverfasser:	Rohekar, Raanan Y, Gurwicz, Yaniv, Shami Nisimov, Novik, Gal
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Bayesian analysis Modelling Neural networks Normal distribution Uncertainty
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!