English
Related papers

Related papers: Single-model uncertainty quantification in neural …

200 papers

The development of large databases of material properties, together with the availability of powerful computers, has allowed machine learning (ML) modeling to become a widely used tool for predicting material performances. While confidence…

Materials Science · Physics 2023-10-23 Francesca Tavazza , Kamal Choudhary , Brian DeCost

Uncertainty quantification (UQ) provides a resource-efficient solution for on-device monitoring of tinyML models deployed without access to true labels. However, existing UQ methods impose significant memory and compute demands, making them…

Machine Learning · Computer Science 2024-11-19 Nikhil P Ghanathe , Steven J E Wilton

Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks. Quantifying predictive uncertainty in NNs is a challenging and yet unsolved problem. Bayesian NNs,…

Machine Learning · Statistics 2017-11-07 Balaji Lakshminarayanan , Alexander Pritzel , Charles Blundell

Inverse Uncertainty Quantification (UQ), or Bayesian calibration, is the process to quantify the uncertainties of random input parameters based on experimental data. The introduction of model discrepancy term is significant because…

Applications · Statistics 2019-07-24 Xu Wu , Koroush Shirvan , Tomasz Kozlowski

Effective potentials are an essential ingredient of classical molecular dynamics (MD) simulations. Little is understood of the consequences of representing the complex energy landscape of an atomic configuration by an effective potential or…

Materials Science · Physics 2019-03-13 Sarah Longbottom , Peter Brommer

Uncertainty quantification (UQ) is essential for deploying deep neural networks in safety-critical settings. Although methods like Deep Ensembles achieve strong UQ performance, their high computational and memory costs hinder scalability to…

Machine Learning · Computer Science 2026-04-22 Firas Gabetni , Giuseppe Curci , Andrea Pilzer , Subhankar Roy , Elisa Ricci , Gianni Franchi

Machine learning (ML) enables the development of interatomic potentials that promise the accuracy of first principles methods while retaining the low cost and parallel efficiency of empirical potentials. While ML potentials traditionally…

Uncertainty quantification (UQ) plays a critical role in verifying and validating forward integrated computational materials engineering (ICME) models. Among numerous ICME models, the crystal plasticity finite element method (CPFEM) is a…

Materials Science · Physics 2023-01-27 Anh Tran , Pieterjan Robbe , Tim Wildey , David Montes de Oca Zapiain , Hojun Lim

This study investigates whether Physically Recurrent Neural Networks (PRNNs), a recent surrogate model for heterogeneous materials, trained on a micromodel with fixed material parameters, can maintain accuracy for varying material…

Disordered Systems and Neural Networks · Physics 2025-04-17 N. Kovács , I. B. C. M. Rocha , F. P. van der Meer , C. Furtado , P. P. Camanho

Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular approaches to estimate…

Large language models (LLMs) exhibit impressive fluency, but often produce critical errors known as "hallucinations". Uncertainty quantification (UQ) methods are a promising tool for coping with this fundamental shortcoming. Yet, existing…

Uncertainty quantification (UQ) is an essential tool for applying deep neural networks (DNNs) to real world tasks, as it attaches a degree of confidence to DNN outputs. However, despite its benefits, UQ is often left out of the standard DNN…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Nils Lehmann , Jakob Gawlikowski , Adam J. Stewart , Vytautas Jancauskas , Stefan Depeweg , Eric Nalisnick , Nina Maria Gottschling

Large Language Diffusion Models (LLDMs) are emerging as an alternative to autoregressive models, offering faster inference through higher parallelism. Similar to autoregressive LLMs, they remain prone to hallucinations, making reliable…

Computation and Language · Computer Science 2026-05-15 Artem Vazhentsev , Vladislav Smirnov , David Li , Maxim Panov , Timothy Baldwin , Artem Shelmanov

Turbulent flows are of central importance across applications in science and engineering problems. For design and analysis, scientists and engineers use Computational Fluid Dynamics (CFD) simulations using turbulence models. Turbulent…

Fluid Dynamics · Physics 2023-10-18 Minghan Chu , Weicheng Qian

Using a cyclotron based model problem, we demonstrate for the first time the applicability and usefulness of a uncertainty quantification (UQ) approach in order to construct surrogate models for quantities such as emittance, energy spread…

Accelerator Physics · Physics 2018-12-13 Andreas Adelmann

Uncertainty quantification has been a core of the statistical machine learning, but its computational bottleneck has been a serious challenge for both Bayesians and frequentists. We propose a model-based framework in quantifying…

Machine Learning · Computer Science 2019-06-04 Minsuk Shin , Young Lee , Jun S. Liu

Uncertainty quantification (UQ) in computational chemistry (CC) is still in its infancy. Very few CC methods are designed to provide a confidence level on their predictions, and most users still rely improperly on the mean absolute error as…

Chemical Physics · Physics 2022-03-21 Pascal Pernot

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Emanuele Ledda , Daniele Angioni , Giorgio Piras , Giorgio Fumera , Battista Biggio , Fabio Roli

Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge. In graph settings, message passing often relies on strong assumptions such as exchangeability, which are…

Machine Learning · Computer Science 2026-05-07 Soyoung park , Hwanjun Song , Sungsu Lim

This paper presents the development and demonstration of massively parallel probabilistic machine learning (ML) and uncertainty quantification (UQ) capabilities within the Multiphysics Object-Oriented Simulation Environment (MOOSE), an…