Browsing Department of Mathematics by Author "Nilsen, Geir Kjetil"

Now showing items 1-2 of 2

Epistemic Uncertainty Quantification in Deep Learning by the Delta Method

Nilsen, Geir Kjetil (Doctoral thesis, 2022-05-16)

This thesis explores the Delta method and its application to deep learning image classification. The Delta method is a classical procedure for quantifying uncertainty in statistical models, but its direct application to ...
Epistemic uncertainty quantification in deep learning classification by the Delta method

Nilsen, Geir Kjetil; Munthe-Kaas, Antonella Zanna; Skaug, Hans Julius; Brun, Morten (Journal article; Peer reviewed, 2022)

The Delta method is a classical procedure for quantifying epistemic uncertainty in statistical models, but its direct application to deep neural networks is prevented by the large number of parameters . We propose a low ...