Timezone: »

 
Poster
Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Joost van Amersfoort · Lewis Smith · Yee-Whye Teh · Yarin Gal

Tue Jul 14 01:00 PM -- 01:45 PM & Wed Jul 15 01:00 AM -- 01:45 AM (PDT) @ Virtual
in Poster Session 7 »

We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), builds upon ideas of RBF networks. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models. By enforcing detectability of changes in the input using a gradient penalty, we are able to reliably detect out of distribution data. Our uncertainty quantification scales well to large datasets, and using a single model, we improve upon or match Deep Ensembles in out of distribution detection on notable difficult dataset pairs such as FashionMNIST vs. MNIST, and CIFAR-10 vs. SVHN.

Keywords: Algorithms · Bayesian Deep Learning · Representation Learning · Supervised Learning
[ Slides] 

Author Information

Joost van Amersfoort (University of Oxford)
Lewis Smith (University of Oxford)

Lewis smith is a DPhil student in Yarin Gals OATML lab at the University of Oxford, in the third year of his studies. Before that he did an undergraduate in Physics at the university of Manchester. His interests are in probabilistic methods, and in particular in structured methods that build in assumptions appropriate to the problem, such as object factorisation or assumptions about invariances.

Yee-Whye Teh (Oxford and DeepMind)
Yarin Gal (University of Oxford)

More from the Same Authors