Getting a CLUE: A Method for Explaining Uncertainty Estimates

Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems. However, there is little work at the intersection of these two areas. We address this gap by proposing a novel method for interpreting uncertainty estimates from differentiable probabilis...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-03
Hauptverfasser:	Antorán, Javier, Bhatt, Umang, Tameem Adel, Weller, Adrian, José Miguel Hernández-Lobato
Format:	Artikel
Sprache:	eng
Schlagworte:	Ablation Machine learning Neural networks Probabilistic models Uncertainty
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!