English
Related papers

Related papers: Uncertainty Quantification of Graph Convolution Ne…

200 papers

Advances in deep neural network (DNN) based molecular property prediction have recently led to the development of models of remarkable accuracy and generalization ability, with graph convolution neural networks (GCNNs) reporting…

Machine Learning · Computer Science 2019-10-09 Gabriele Scalia , Colin A. Grambow , Barbara Pernici , Yi-Pei Li , William H. Green

Uncertainty quantification (UQ) techniques are frequently used to ascertain output variability in systems with parametric uncertainty. Traditional algorithms for UQ are either system-agnostic and slow (such as Monte Carlo) or fast with…

Computation · Statistics 2015-03-19 Tuhin Sahai , Jose Miguel Pasini

Convolutional neural networks have shown to achieve superior performance on image segmentation tasks. However, convolutional neural networks, operating as black-box systems, generally do not provide a reliable measure about the confidence…

Computer Vision and Pattern Recognition · Computer Science 2020-07-20 Alexander Treiss , Jannis Walk , Niklas Kühl

The Monte Carlo (MC) method is the most common technique used for uncertainty quantification, due to its simplicity and good statistical results. However, its computational cost is extremely high, and, in many cases, prohibitive.…

Computation · Statistics 2021-05-21 A. Cunha , R. Nasser , R. Sampaio , H. Lopes , K. Breitman

Traditional deep learning (DL) models are powerful classifiers, but many approaches do not provide uncertainties for their estimates. Uncertainty quantification (UQ) methods for DL models have received increased attention in the literature…

Machine Learning · Computer Science 2023-08-14 Daniel Ries , Joshua Michalenko , Tyler Ganter , Rashad Imad-Fayez Baiyasi , Jason Adams

Uncertainty quantification of deep neural networks has become an active field of research and plays a crucial role in various downstream tasks such as active learning. Recent advances in evidential deep learning shed light on the direct…

Machine Learning · Computer Science 2023-11-21 Ruxiao Duan , Brian Caffo , Harrison X. Bai , Haris I. Sair , Craig Jones

Particle-based approximate Bayesian inference approaches such as Stein Variational Gradient Descent (SVGD) combine the flexibility and convergence guarantees of sampling methods with the computational benefits of variational inference. In…

Machine Learning · Computer Science 2021-07-30 Lauro Langosco di Langosco , Vincent Fortuin , Heiko Strathmann

Probabilistic graphical models are a fundamental tool in probabilistic modeling, machine learning and artificial intelligence. They allow us to integrate in a natural way expert knowledge, physical modeling, heterogeneous and correlated…

Machine Learning · Statistics 2021-07-20 Panagiota Birmpa , Jinchao Feng , Markos A. Katsoulakis , Luc Rey-Bellet

Machine learning methods such as convolutional neural networks (CNNs) are becoming an integral part of scientific research in many disciplines, spatial vector data often fail to be analyzed using these powerful learning methods because of…

Machine Learning · Statistics 2018-09-24 Xiongfeng Yan , Tinghua Ai

Subsurface flow problems usually involve some degree of uncertainty. Consequently, uncertainty quantification is commonly necessary for subsurface flow prediction. In this work, we propose a methodology for efficient uncertainty…

Signal Processing · Electrical Eng. & Systems 2020-12-02 Nanzhe Wang , Haibin Chang , Dongxiao Zhang

The accessibility of spatially distributed data, enabled by affordable sensors, field, and numerical experiments, has facilitated the development of data-driven solutions for scientific problems, including climate change, weather…

Machine Learning · Computer Science 2023-11-09 Vardhan Dongre , Gurpreet Singh Hora

Predicting the evolution of turbulent flows is central across science and engineering. Most studies rely on simulations with turbulence models, whose empirical simplifications introduce epistemic uncertainty. The Eigenspace Perturbation…

Machine Learning · Computer Science 2025-11-11 Minghan Chu , Weicheng Qian

For many applications it is critical to know the uncertainty of a neural network's predictions. While a variety of neural network parameter estimation methods have been proposed for uncertainty estimation, they have not been rigorously…

Machine Learning · Computer Science 2019-12-05 Nabeel Seedat , Christopher Kanan

Stein discrepancies (SDs) monitor convergence and non-convergence in approximate inference when exact integration and sampling are intractable. However, the computation of a Stein discrepancy can be prohibitive if the Stein operator - often…

Machine Learning · Statistics 2020-10-26 Jackson Gorham , Anant Raj , Lester Mackey

Process mining is a discipline which concerns the analysis of execution data of operational processes, the extraction of models from event data, the measurement of the conformance between event data and normative models, and the enhancement…

Data Structures and Algorithms · Computer Science 2022-04-09 Marco Pegoraro , Merih Seran Uysal , Wil M. P. van der Aalst

The usual figure of merit characterizing the performance of neural networks applied to problems in the quantum domain is their accuracy, being the probability of a correct answer on a previously unseen input. Here we append this parameter…

Quantum Physics · Physics 2022-12-29 Jan Wasilewski , Tomasz Paterek , Karol Horodecki

Deep unrolling is an emerging deep learning-based image reconstruction methodology that bridges the gap between model-based and purely deep learning-based image reconstruction methods. Although deep unrolling methods achieve…

Image and Video Processing · Electrical Eng. & Systems 2022-12-21 Canberk Ekmekci , Mujdat Cetin

The hybrid neural differentiable models mark a significant advancement in the field of scientific machine learning. These models, integrating numerical representations of known physics into deep neural networks, offer enhanced predictive…

Machine Learning · Computer Science 2024-01-02 Deepak Akhare , Tengfei Luo , Jian-Xun Wang

Deep neural networks offer numerous potential applications across geoscience, for example, one could argue that they are the state-of-the-art method for predicting faults in seismic datasets. In quantitative reservoir characterization…

Machine Learning · Computer Science 2021-05-26 Lukas Mosser , Ehsan Zabihi Naeini

Among Bayesian methods, Monte-Carlo dropout provides principled tools for evaluating the epistemic uncertainty of neural networks. Its popularity recently led to seminal works that proposed activating the dropout layers only during…

Machine Learning · Computer Science 2023-02-07 Emanuele Ledda , Giorgio Fumera , Fabio Roli