A new reliability score computed from the IoU difference between class-specific and class-agnostic heatmaps, boosted by adversarial enhancement, detects false negatives in binary industrial defect detectors with up to 100% recall.
Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
PLAG boosts tabular anomaly detection by using pseudo-label-guided synthetic anomaly generation with a two-stage filter, achieving SOTA results and lifting F1 scores by 0.08-0.21 when added to existing detectors.
Derives a posterior-predictive variance decomposition separating epistemic and aleatoric uncertainty in heteroscedastic Bayesian neural network models for wind power forecasting, with a dedicated validation framework tested on synthetic and real SCADA data.
Diffusion sampler framework produces intrinsically calibrated predictive uncertainty for industrial soft sensors and process models via faithful posterior sampling.
citing papers explorer
-
When Can We Trust Deep Neural Networks? Towards Reliable Industrial Deployment with an Interpretability Guide
A new reliability score computed from the IoU difference between class-specific and class-agnostic heatmaps, boosted by adversarial enhancement, detects false negatives in binary industrial defect detectors with up to 100% recall.
-
Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation
PLAG boosts tabular anomaly detection by using pseudo-label-guided synthetic anomaly generation with a two-stage filter, achieving SOTA results and lifting F1 scores by 0.08-0.21 when added to existing detectors.
-
A Posterior-Predictive Variance Decomposition for Epistemic and Aleatoric Uncertainty in Wind Power Forecasting
Derives a posterior-predictive variance decomposition separating epistemic and aleatoric uncertainty in heteroscedastic Bayesian neural network models for wind power forecasting, with a dedicated validation framework tested on synthetic and real SCADA data.
-
Towards Intrinsically Calibrated Uncertainty Quantification in Industrial Data-Driven Models via Diffusion Sampler
Diffusion sampler framework produces intrinsically calibrated predictive uncertainty for industrial soft sensors and process models via faithful posterior sampling.