Probabilistic neural data fusion for learning from an arbitrary number of multi-fidelity data sets

DOI10.1016/j.cma.2023.116207arXiv2301.13271MaRDI QIDQ6096443

Tyler Johnson, Carlos M. Mora, Likith Gadde, Ramin Bostanabad, Jonathan Tammer Eweis-Labolle

Publication date: 12 September 2023

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2301.13271

zbMATH Keywords

inverse problemsdata fusionuncertainty quantificationmanifold learningmulti-fidelity modelingBayesian neural networks

Mathematics Subject Classification ID

Biology and other natural sciences (92-XX) Computer science (68-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Calibrating a large computer experiment simulating radiative shock hydrodynamics
• Multivariate significance testing and model calibration under uncertainty
• Multilayer feedforward networks are universal approximators
• Multi-fidelity design optimisation strategy under uncertainty with limited computational budget
• A composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problems
• Bi-fidelity approximation for uncertainty quantification and sensitivity analysis of irradiated particle-laden turbulence
• Latent map Gaussian processes for mixed variable metamodeling
• A surrogate based multi-fidelity approach for robust design optimization
• Diffusion maps
• Variable-resolution shape optimisation: Low-fidelity model selection and scalability
• MFNets: data efficient all-at-once learning of multifidelity surrogates as directed networks of information sources
• Multi-fidelity cost-aware Bayesian optimization
• Bayesian Calibration of Computer Models
• Representing Model Inadequacy: A Stochastic Operator Approach
• Combining Field Data and Computer Simulations for Calibration and Prediction
• ON TRANSFER LEARNING OF NEURAL NETWORKS USING BI-FIDELITY DATA FOR UNCERTAINTY PROPAGATION
• MFNets: MULTI-FIDELITY DATA-DRIVEN NETWORKS FOR BAYESIAN LEARNING AND PREDICTION
• An Adaptive Surrogate Modeling Based on Deep Neural Networks for Large-Scale Bayesian Inverse Problems
• Strictly Proper Scoring Rules, Prediction, and Estimation
• Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
• Monte Carlo sampling methods using Markov chains and their applications
• Adaptive spatiotemporal dimension reduction in concurrent multiscale damage analysis

This page was built for publication: Probabilistic neural data fusion for learning from an arbitrary number of multi-fidelity data sets