Results 21 to 30 of about 1,009,621 (180)
One Step Closer to Unbiased Aleatoric Uncertainty Estimation
Proceedings of the AAAI Conference on Artificial IntelligenceNeural 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) uncertainty.
Wang Zhang +6 more
openaire +5 more sources
Rethinking Aleatoric and Epistemic Uncertainty [PDF]
CoRRPublished at ICML ...
Bickford Smith, F +5 more
openaire +6 more sources
Identifying Drivers of Predictive Aleatoric Uncertainty [PDF]
Proceedings of the Thirty-Fourth International Joint Conference on Artificial IntelligenceExplainability and uncertainty quantification are key to trustable artificial intelligence. However, the reasoning behind uncertainty estimates is generally left unexplained. Identifying the drivers of uncertainty complements explanations of point predictions in recognizing model limitations and enhancing transparent decision-making.
Pascal Iversen +3 more
core +4 more sources
Epistemic and aleatoric uncertainty quantification in weather and climate models
Quarterly Journal of the Royal Meteorological SocietyAbstract Representing and quantifying uncertainty in physical parameterisations is a central challenge in weather and climate modelling, and approaches are often developed separately for different time‐scales. Here, we introduce a unified framework for analysing uncertainty in parameterisations across weather and climate regimes ...
Laura A. Mansfield +1 more
openaire +3 more sources
Estimating Epistemic and Aleatoric Uncertainty with a Single Model
Advances in Neural Information Processing Systems 37Estimating and disentangling epistemic uncertainty, uncertainty that is reducible with more training data, and aleatoric uncertainty, uncertainty that is inherent to the task at hand, is critically important when applying machine learning to high-stakes applications such as medical imaging and weather forecasting.
Matthew Chan +2 more
openaire +4 more sources
Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling [PDF]
, 2023 In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions. To this end, we propose an ensemble of Normalizing Flows (NF), which are state-of-the-art
Meger, David, Berry, Lucas
core +3 more sources
Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rules [PDF]
CoRRUncertainty representation and quantification are paramount in machine learning and constitute an important prerequisite for safety-critical applications. In this paper, we propose novel measures for the quantification of aleatoric and epistemic uncertainty based on proper scoring rules, which are loss functions with the meaningful property that they ...
Paul Hofman +2 more
core +5 more sources
Intrinsic randomness in epidemic modelling beyond statistical uncertainty
Communications Physics, 2023 Uncertainty can be classified as either aleatoric (intrinsic randomness) or epistemic (imperfect knowledge of parameters). The majority of frameworks assessing infectious disease risk consider only epistemic uncertainty.
Matthew J. Penn +9 more
doaj +1 more source
Looking at the posterior: accuracy and uncertainty of neural-network predictions
Machine Learning: Science and Technology, 2023 Bayesian inference can quantify uncertainty in the predictions of neural networks using posterior distributions for model parameters and network output.
Hampus Linander +3 more
doaj +1 more source
Grounding Aleatoric Uncertainty for Unsupervised Environment Design
Advances in Neural Information Processing Systems 35, 2022 NeurIPS ...
Minqi Jiang +7 more
openaire +3 more sources