Uncertainty in Deep Learning
GPTKB entity
Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
research
|
| gptkbp:application |
natural language processing
autonomous driving medical imaging |
| gptkbp:goal |
detect out-of-distribution data
enable risk-aware decision making improve model robustness quantify model confidence |
| gptkbp:hasType |
aleatoric uncertainty
epistemic uncertainty |
| https://www.w3.org/2000/01/rdf-schema#label |
Uncertainty in Deep Learning
|
| gptkbp:importantConference |
gptkb:ICLR
gptkb:ICML gptkb:NeurIPS |
| gptkbp:importantPaper |
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (Alex Kendall, Yarin Gal, 2017)
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning (Yarin Gal, Zoubin Ghahramani, 2016) |
| gptkbp:method |
gptkb:Variational_inference
Bayesian neural networks Ensemble methods Monte Carlo dropout Test-time data augmentation |
| gptkbp:relatedTo |
gptkb:machine_learning
deep learning probabilistic modeling |
| gptkbp:studiedBy |
gptkb:Zoubin_Ghahramani
gptkb:Yarin_Gal |
| gptkbp:bfsParent |
gptkb:Yarin_Gal
|
| gptkbp:bfsLayer |
8
|