Results 31 to 40 of about 1,009,621 (180)
LogSE: An Uncertainty-Based Multi-Task Loss Function for Learning Two Regression Tasks [PDF]
Journal of Universal Computer Science, 2022 Multi-task learning (MTL) is a popular method in machine learning which utilizes related information of multi tasks to learn a task more efficiently and accurately.
Zeinab Ghasemi-Naraghi +2 more
doaj +3 more sources
Quantifying uncertainty of machine learning methods for loss given default
Frontiers in Applied Mathematics and Statistics, 2022 Machine learning has increasingly found its way into the credit risk literature. When applied to forecasting credit risk parameters, the approaches have been found to outperform standard statistical models. The quantification of prediction uncertainty is
Matthias Nagl +2 more
doaj +1 more source
Cold Posteriors and Aleatoric Uncertainty
CoRR, 2020 5 pages, 3 ...
Ben Adlam, Jasper Snoek, Samuel L. Smith
openaire +2 more sources
SN Applied Sciences, 2022 The deep convolutional neural network (ConvNet) achieves significant segmentation performance on medical images of various modalities. However, the isolated errors in a large testing set with various tumor conditions are not acceptable in clinical ...
Ge Zhang, Hao Dang, Yulong Xu
doaj +1 more source
Recalibration of Aleatoric and EpistemicRegression Uncertainty in Medical Imaging
Machine Learning for Biomedical Imaging, 2021 The consideration of predictive uncertainty in medical imaging with deep learning is of utmost importance. We apply estimation of both aleatoric and epistemic uncertainty by variational Bayesian inference with Monte Carlo dropout to regression tasks and show that predictive uncertainty is systematically underestimated.
Max-Heinrich Laves +4 more
openaire +2 more sources
Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods [PDF]
Machine Learning, 2021 AbstractThe notion of uncertainty is of major importance in machine learning and constitutes a key element of machine learning methodology. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions.
Eyke Hüllermeier, Willem Waegeman
openaire +6 more sources
Aleatoric Uncertainty for Errors-in-Variables Models in Deep Regression
Neural Processing Letters, 2022 AbstractA Bayesian treatment of deep learning allows for the computation of uncertainties associated with the predictions of deep neural networks. We show how the concept of Errors-in-Variables can be used in Bayesian deep regression to also account for the uncertainty associated with the input of the employed neural network.
Jörg Martin, Clemens Elster
openaire +2 more sources
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 ICCV 2021 (oral)
Gwangbin Bae +2 more
openaire +3 more sources
One step closer to unbiased aleatoric uncertainty estimation [PDF]
, 2023 Neural networks are powerful tools in various applications, and quantifying their uncertainty is crucial for reliable decision-making. In the deep learning field, the uncertainties are usually categorized into aleatoric (data) and epistemic (model ...
Megretski, Alexandre +6 more
core +1 more source
How to measure uncertainty in uncertainty sampling for active learning [PDF]
, 2022 Various strategies for active learning have been proposed in the machine learning literature. In uncertainty sampling, which is among the most popular approaches, the active learner sequentially queries the label of those instances for which its current ...
Hüllermeier, Eyke +3 more
core +2 more sources