Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement
Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, some methods like Flipout produce zero epistemic uncertainty, aleatoric uncertainty is unreliable in the out-of-distribution setting, and Ensembles provide overall the best disentangling quality. We also explore the error produced by the number of samples hyper-parameter in the sampling softmax function, recommending N > 100 samples. We expect that our formulation and results help practitioners and researchers choose uncertainty methods and expand the use of disentangled uncertainties, as well as motivate additional research into this topic.
A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement
Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, some methods like Flipout produce zero epistemic uncertainty, aleatoric uncertainty is unreliable in the out-of-distribution setting, and Ensembles provide overall the best disentangling quality. We also explore the error produced by the number of samples hyper-parameter in the sampling softmax function, recommending N > 100 samples. We expect that our formulation and results help practitioners and researchers choose uncertainty methods and expand the use of disentangled uncertainties, as well as motivate additional research into this topic.
A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement
Valdenegro-Toro, Matias (Autor:in) / Saromo, Daniel (Autor:in)
23.08.2022
Valdenegro-Toro , M & Saromo , D 2022 , A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement . in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . IEEE , pp. 1508-1516 , IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops , New Orleans, LA , 19/06/2022 . https://doi.org/10.1109/CVPRW56347.2022.00157
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC:
690
| British Library Online Contents | 2010
| British Library Online Contents | 2010