Results 101 to 110 of about 7,687 (182)

Performance of Conformal Prediction in Capturing Aleatoric Uncertainty

Accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV ...
Hagos, Misgina Tsighe, Lundström, Claes
openaire   +2 more sources

Uncertainty quantification for scientific machine learning using sparse variational Gaussian process Kolmogorov–Arnold networks (SVGP KAN)

Machine Learning: Science and Technology
Kolmogorov–Arnold networks (KANs) have emerged as interpretable alternatives to traditional multi-layer perceptrons. However, standard implementations lack principled uncertainty quantification capabilities essential for many scientific applications.
Y Sungtaek Ju
doaj   +1 more source

Finer Disentanglement of Aleatoric Uncertainty Can Accelerate Chemical Histopathology Imaging

Label-free chemical imaging holds significant promise for improving digital pathology workflows, but data acquisition speed remains a limiting factor. To address this gap, we propose an adaptive strategy-initially scan the low information (LI) content of the entire tissue quickly, identify regions with high aleatoric uncertainty (AU), and selectively ...
Oh, Ji-Hun, Falahkheirkhah, Kianoush, Bhargava, Rohit   +2 more
openaire   +2 more sources

Estimating Epistemic and Aleatoric Uncertainty with a Single Model

Advances in Neural Information Processing Systems 37
Estimating 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.
Chan, Matthew A., Molina, Maria J., Metzler, Christopher A.   +2 more
openaire   +2 more sources

Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Computer vision systems that are deployed in safety-critical applications need to quantify their output uncertainty. We study regression from images to parameter values and here it is common to detect uncertainty by predicting probability distributions.
Xiong, Ziliang, Jonnarth, Arvi, Eldesokey, Abdelrahman, Johnander, Joakim, Wandt, Bastian, Forssén, Per-Erik   +5 more
openaire   +3 more sources

Uncertainty aware predictive maintenance using a hybrid Transformer with Monte Carlo Dropout and conformal prediction

Ain Shams Engineering Journal
Predictive maintenance (PdM) relies on accurate estimation of the remaining useful life (RUL) to support efficient industrial maintenance. However, most RUL models overlook uncertainty quantification (UQ), which is essential for safety–critical decision ...
Chao-Lung Yang, Tamrat Yifter Meles, Atinkut Atinafu Yilma, Melkamu Mengstnew Teshome   +3 more
doaj   +1 more source

Uncertainty propagation in the internet of things

Discover Internet of Things
The Internet of Things (IoT) detects context through sensors capturing data from dynamic physical environments, in order to inform automation decisions within cyber physical systems (CPS).
Shantanu Pal, Sara Khalifa, Dimity Miller, Volkan Dedeoglu, Ali Dorri, Gowri Ramachandran, Peyman Moghadam, Brano Kusy, Raja Jurdak   +8 more
doaj   +1 more source

Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rules

Uncertainty 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 ...
Hofman, Paul, Sale, Yusuf, Hüllermeier, Eyke   +2 more
openaire   +2 more sources

Aleatoric Uncertainty Modelling in Regression Problems using Deep Learning

, 2022
Programa de Doctorat en Matemàtica i ...
openaire   +2 more sources

Organic Solubility Prediction at the Limit of Aleatoric Uncertainty

Small molecule solubility is a critically important property which affects the efficiency, environmental impact, and phase behavior of synthetic processes. Experimental determination of solubility is a time- and resource-intensive process and existing methods for in silico estimation of solubility are limited by their generality, speed, and accuracy ...
Lucas Attia, Jackson W. Burns, Patrick S. Doyle, William H. Green   +3 more
openaire   +1 more source