A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks

Physics-informed neural networks (PINNs) have shown to be effective tools for solving both forward and inverse problems of partial differential equations (PDEs). PINNs embed the PDEs into the loss of the neural network using automatic differentiation, and this PDE loss is evaluated at a set of scatt...

Full description

Saved in:

Bibliographic Details
Published in:	Computer methods in applied mechanics and engineering Vol. 403; no. PA; p. 115671
Main Authors:	Wu, Chenxi, Zhu, Min, Tan, Qinyang, Kartha, Yadhu, Lu, Lu
Format:	Journal Article
Language:	English
Published:	Amsterdam Elsevier B.V 01.01.2023 Elsevier BV Elsevier
Subjects:	Adaptive sampling Hammersley sequence Hypercubes Inverse problems Latin hypercube sampling Neural networks Non-adaptive uniform sampling Partial differential equations Physics-informed neural networks Random sampling Resampling Residual point distribution Residual-based adaptive sampling Sampling methods Uniform sampling with resampling Residual point distribution Non-adaptive uniform sampling Partial differential equations Residual-based adaptive sampling Uniform sampling with resampling Physics-informed neural networks
ISSN:	0045-7825, 1879-2138
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!