2020
DOI: 10.1007/978-3-030-50146-4_41
|View full text |Cite
|
Sign up to set email alerts
|

Evaluation of Uncertainty Quantification in Deep Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
17
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
4
2

Relationship

0
10

Authors

Journals

citations
Cited by 33 publications
(17 citation statements)
references
References 14 publications
0
17
0
Order By: Relevance
“…Future work will explore how the bias between high measurements and high uncertainty can be corrected for and may also consider alternative strategies which are known to produce substantially distinct estimates of uncertainty [30]. However, it is unclear whether Monte-Carlo techniques that employ dropout at test time [31] could reach sufficient predictive performance, whereas more faithful approximations of Bayesian inference with Markov chain Monte-Carlo [32] may not be computationally viable.…”
Section: Discussionmentioning
confidence: 99%
“…Future work will explore how the bias between high measurements and high uncertainty can be corrected for and may also consider alternative strategies which are known to produce substantially distinct estimates of uncertainty [30]. However, it is unclear whether Monte-Carlo techniques that employ dropout at test time [31] could reach sufficient predictive performance, whereas more faithful approximations of Bayesian inference with Markov chain Monte-Carlo [32] may not be computationally viable.…”
Section: Discussionmentioning
confidence: 99%
“…Alternative methods are based, indicatively, on ensembles of NN optimization iterates or independently trained NNs [39][40][41][42][43][44][45][46][47][48][49][50], as well as on the evidential framework [51][52][53][54][55][56][57][58][59]. Although Bayesian methods and ensembles are thoroughly discussed in this paper, the interested reader is also directed to the recent review studies in [60][61][62][63][64][65][66][67][68][69][70][71][72] for more information. Clearly, in the context of SciML, which may involve differential equations with unknown or uncertain terms and parameters, UQ becomes an even more demanding task; see Fig.…”
Section: Motivation and Scope Of The Papermentioning
confidence: 99%
“…As the variation among the data in aleatory uncertainty is often observable, we can well quantify the uncertainty and assess the risks. Quantification of epistemic uncertainty is more challenging because AI systems are forced to extrapolate over unseen situations (Ståhl, Falkman, Karlsson, & Mathiason, 2020). In the literature of uncertainty quantification, one of the most widely recognized techniques are prediction intervals (PI).…”
Section: Uncertainty Quantificationmentioning
confidence: 99%