2022
DOI: 10.48550/arxiv.2209.08418
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Sample-based Uncertainty Quantification with a Single Deterministic Neural Network

Abstract: Development of an accurate, flexible, and numerically efficient uncertainty quantification (UQ) method is one of fundamental challenges in machine learning. Previously, a UQ method called DISCO Nets has been proposed (Bouchacourt et al., 2016) that trains a neural network by minimizing the so-called energy score on training data. This method has shown superior performance on a hand pose estimation task in computer vision, but it remained unclear whether this method works as nicely for regression on tabular dat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 44 publications
0
1
0
Order By: Relevance
“…This survey only includes confidence calibration methods that can be used in deep learning models under class imbalance data. Uncertainty estimation [31], [32], [33], [34], [35], [36], [37] and confidence calibration are two similar but different concepts. The former only perceives the uncertainty of prediction, while the latter requires accurate probability estimation.…”
Section: B Survey Scopementioning
confidence: 99%
“…This survey only includes confidence calibration methods that can be used in deep learning models under class imbalance data. Uncertainty estimation [31], [32], [33], [34], [35], [36], [37] and confidence calibration are two similar but different concepts. The former only perceives the uncertainty of prediction, while the latter requires accurate probability estimation.…”
Section: B Survey Scopementioning
confidence: 99%