[HTML][HTML] Evaluation of uncertainty quantification methods in multi-label classification: A case study with automatic diagnosis of electrocardiogram

M Barandas, L Famiglini, A Campagner, D Folgado… - Information …, 2024 - Elsevier
Artificial Intelligence (AI) use in automated Electrocardiogram (ECG) classification has
continuously attracted the research community's interest, motivated by their promising …

Analytical uncertainty propagation in neural networks

P Jungmann, J Poray, A Kumar - IEEE Transactions on Neural …, 2024 - ieeexplore.ieee.org
The usage of machine-learning techniques, such as neural networks, is common in a large
variety of domains. Estimating the certainty of a predicted value is important when precise …

BaSIS-Net: From point estimate to predictive distribution in neural networks-a Bayesian sequential importance sampling framework

G Carannante, N Bouaynaya… - Transactions on …, 2024 - eprints.whiterose.ac.uk
Data-driven Deep Learning (DL) models have revolutionized autonomous systems, but
ensuring their safety and reliability necessitates the assessment of predictive confidence or …

Improving Uncertainty Quantification of Variance Networks by Tree-Structured Learning

W Ma, X Yan, K Zhang - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
To improve the uncertainty quantification of variance networks, we propose a novel tree-
structured local neural network model that partitions the feature space into multiple regions …

[PDF][PDF] UNCERTAINTY IN MACHINE LEARNING

MDASG BARANDAS - 2023 - run.unl.pt
Uncertainty is an inevitable and essential aspect of the world we live in and a fundamental
aspect of human decision-making. It is no different in the realm of machine learning. Just as …

Uncertainty in Machine Learning a Safety Perspective on Biomedical Applications

MSG Barandas - 2023 - search.proquest.com
Uncertainty is an inevitable and essential aspect of the worldwe live in and a fundamental
aspect of human decision-making. It is no different in the realm of machine learning. Just as …