Scalable Moment Propagation and Analysis of Variational Distributions for Practical Bayesian Deep Learning

Bayesian deep learning is one of the key frameworks employed in handling predictive uncertainty. Variational inference (VI), an extensively used inference method, derives the predictive distributions by Monte Carlo (MC) sampling. The drawback of MC sampling is its extremely high computational cost c...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2024-02, Vol.PP, p.1-11
Hauptverfasser:	Hirayama, Yuki, Takamaeda-Yamazaki, Shinya
Format:	Artikel
Sprache:	eng
Schlagworte:	Bayes methods Bayesian convolutional neural network (CNN) Bayesian deep learning Covariance matrices Deep learning Gaussian distribution moment propagation (MP) Neural networks Task analysis Uncertainty uncertainty estimation variational inference (VI)
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!