Exploring the relationship between segmentation uncertainty, segmentation performance and inter-observer variability with probabilistic networks
E Chotzoglou, B Kainz - Large-Scale Annotation of Biomedical Data and …, 2019 - Springer
Medical image segmentation is an essential tool for clinical decision making and treatment
planning. Automation of this process led to significant improvements in diagnostics and …
planning. Automation of this process led to significant improvements in diagnostics and …
Quantifying uncertainty in graph neural network explanations
In recent years, analyzing the explanation for the prediction of Graph Neural Networks
(GNNs) has attracted increasing attention. Despite this progress, most existing methods do …
(GNNs) has attracted increasing attention. Despite this progress, most existing methods do …
A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning
F Fakour, A Mosleh, R Ramezani - arXiv preprint arXiv:2406.00332, 2024 - arxiv.org
The adaptation and use of Machine Learning (ML) in our daily lives has led to concerns in
lack of transparency, privacy, reliability, among others. As a result, we are seeing research in …
lack of transparency, privacy, reliability, among others. As a result, we are seeing research in …
[图书][B] Hamiltonian Monte Carlo methods in machine learning
Hamiltonian Monte Carlo Methods in Machine Learning introduces methods for optimal
tuning of HMC parameters, along with an introduction of Shadow and Non-canonical HMC …
tuning of HMC parameters, along with an introduction of Shadow and Non-canonical HMC …
A view on model misspecification in uncertainty quantification
Estimating uncertainty of machine learning models is essential to assess the quality of the
predictions that these models provide. However, there are several factors that influence the …
predictions that these models provide. However, there are several factors that influence the …
Comparison of uncertainty quantification with deep learning in time series regression
L Foldesi, M Valdenegro-Toro - arXiv preprint arXiv:2211.06233, 2022 - arxiv.org
Increasingly high-stakes decisions are made using neural networks in order to make
predictions. Specifically, meteorologists and hedge funds apply these techniques to time …
predictions. Specifically, meteorologists and hedge funds apply these techniques to time …
Decorrelative Network Architecture for Robust Electrocardiogram Classification
C Wiedeman, G Wang - arXiv preprint arXiv:2207.09031, 2022 - arxiv.org
Artificial intelligence has made great progress in medical data analysis, but the lack of
robustness and trustworthiness has kept these methods from being widely deployed. As it is …
robustness and trustworthiness has kept these methods from being widely deployed. As it is …
Tiny Deep Ensemble: Uncertainty Estimation in Edge AI Accelerators via Ensembling Normalization Layers with Shared Weights
ST Ahmed, M Hefenbrock, MB Tahoori - arXiv preprint arXiv:2405.05286, 2024 - arxiv.org
The applications of artificial intelligence (AI) are rapidly evolving, and they are also
commonly used in safety-critical domains, such as autonomous driving and medical …
commonly used in safety-critical domains, such as autonomous driving and medical …
Towards Entity-Aware Conditional Variational Inference for Heterogeneous Time-Series Prediction: An application to Hydrology
Many environmental systems (eg, hydrology basins) can be modeled as entity whose
response (eg, streamflow) depends on drivers (eg, weather) conditioned on their …
response (eg, streamflow) depends on drivers (eg, weather) conditioned on their …
Data-Driven Prediction and Uncertainty Quantification of PWR Crud-Induced Power Shift Using Convolutional Neural Networks
The development of Crud-Induced Power Shift (CIPS) is an operational challenge in
Pressurized Water Reactors that is due to the development of crud on the fuel rod cladding …
Pressurized Water Reactors that is due to the development of crud on the fuel rod cladding …