ERROR ESTIMATES OF RESIDUAL MINIMIZATION USING NEURAL NETWORKS FOR LINEAR PDES
Journal of Machine Learning for Modeling and Computing · 2023 · 4 (4) · 73-101
DOI: 10.1615/jmachlearnmodelcomput.2023050411 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Machine Learning for Modeling and Computing, 2023. Verfasst von Yeonjong Shin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 63 Literaturangaben.
Abstract (Originalsprache)
We propose an abstract framework for analyzing the convergence of least-squares methods based on residual minimization when feasible solutions are neural networks. With the norm relations and compactness arguments, we derive error estimates for both continuous and discrete formulations of residual minimization in strong and weak forms. The formulations cover recently developed physicsinformed neural networks based on strong and variational formulations.
Zitieren
APA
Shin, Y., Zhang, Z., & Karniadakis, G. E. (2023). ERROR ESTIMATES OF RESIDUAL MINIMIZATION USING NEURAL NETWORKS FOR LINEAR PDES. Journal of Machine Learning for Modeling and Computing, 4(4), 73-101. https://doi.org/10.1615/jmachlearnmodelcomput.2023050411
Vancouver
Shin Y, Zhang Z, Karniadakis GE. ERROR ESTIMATES OF RESIDUAL MINIMIZATION USING NEURAL NETWORKS FOR LINEAR PDES. Journal of Machine Learning for Modeling and Computing. 2023;4(4):73-101. doi:10.1615/jmachlearnmodelcomput.2023050411
BibTeX
@article{Shin2023,
author = {Shin, Yeonjong and Zhang, Zhongqiang and Karniadakis, George Em},
title = {ERROR ESTIMATES OF RESIDUAL MINIMIZATION USING NEURAL NETWORKS FOR LINEAR PDES},
journal = {Journal of Machine Learning for Modeling and Computing},
year = {2023},
volume = {4},
number = {4},
pages = {73--101},
doi = {10.1615/jmachlearnmodelcomput.2023050411}
}
EUVIMED