A multi-fidelity transfer learning strategy based on multi-channel fusion

DOI10.1016/J.JCP.2024.112952MaRDI QIDQ6498489zbMATH OpenFDO

Authors Zihan Zhang, Qian Ye, DeJin Yang, Na Wang, Guo-Xiang Meng

Publication date 7 May 2024

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2024.112952

zbMATH Keywords

data fusiondeep neural networksmulti-fidelitysurrogate modeltransfer learning

Mathematics Subject Classification ID

Approximations and expansions (41Axx) Numerical approximation and computational geometry (primarily algorithms) (65Dxx) Artificial intelligence (68Txx)

Recommendations

• Active learning-assisted multi-fidelity surrogate modeling based on geometric transformation
• Transfer learning based multi-fidelity physics informed deep neural network
• A latent variable approach for non-hierarchical multi-fidelity adaptive sampling
• Feature-adjacent multi-fidelity physics-informed machine learning for partial differential equations

Cites work

• A composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problems
• A MULTI-FIDELITY NEURAL NETWORK SURROGATE SAMPLING METHOD FOR UNCERTAINTY QUANTIFICATION
• Efficient model reduction of parametrized systems by matrix discrete empirical interpolation
• scientific article; zbMATH DE number 1795892 (Why is no real title available?)
• Inferring solutions of differential equations using noisy multi-fidelity data
• Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization
• Multi-fidelity optimization via surrogate modelling
• Multi-fidelity regression using artificial neural networks: efficient approximation of parameter-dependent output quantities
• Multifidelity data fusion in convolutional encoder/decoder networks
• Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling
• Nonparametric guidance of autoencoder representations using label information
• Shape optimization of an acoustic horn.
• Surfaces Generated by Moving Least Squares Methods
• The approximation power of moving least-squares
• Transfer learning based multi-fidelity physics informed deep neural network
• Why does unsupervised pre-training help deep learning?

Cited in

(2)

• A latent variable approach for non-hierarchical multi-fidelity adaptive sampling
• Active learning-assisted multi-fidelity surrogate modeling based on geometric transformation

This page was built for publication: A multi-fidelity transfer learning strategy based on multi-channel fusion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6498489)