Grimm, Viktor 
ORCID: 0000-0001-5300-3705, Heinlein, Alexander ORCID: 0000-0003-1578-8104 and Klawonn, Axel ORCID: 0000-0003-4765-7387
(2022).
A short note on solving partial differential equations using convolutional neural networks.
Technical Report.
![[thumbnail of CDS_TR-2022-07.pdf]](http://kups.ub.uni-koeln.de/style/images/fileicons/application_pdf.png "CDS_TR-2022-07.pdf") |
PDF
CDS_TR-2022-07.pdf Bereitstellung unter der CC-Lizenz: Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) |
Abstract
The approach of using physics-based machine learning to solve PDEs has recently become very popular. A recent approach to solve PDEs based on CNNs uses finite difference stencils to include the residual of the partial differential equation into the loss function. In this work, the relation between the network training and the solution of a respective finite difference linear system of equations using classical numerical solvers is discussed. It turns out that many beneficial properties of the linear equation system are neglected in the network training. Finally, numerical results which underline the benefits of classical numerical solvers are presented.
| Item Type: | Monograph (Technical Report) |
| Creators: | Creators Email ORCID ORCID Put Code |
| URN: | urn:nbn:de:hbz:38-642271 |
| Series Name at the University of Cologne: | Technical report series. Center for Data and Simulation Science |
| Volume: | 2022-07 |
| Number of Pages: | 9 |
| Date: | 29 November 2022 |
| Language: | English |
| Faculty: | Central Institutions / Interdisciplinary Research Centers |
| Divisions: | Center for Data and Simulation Science |
| Subjects: | Natural sciences and mathematics Mathematics Technology (Applied sciences) |
| Uncontrolled Keywords: | Keywords Language iterative solvers English convolutional neural networks English physics-informed machine learning English |
| Refereed: | No |
| URI: | http://kups.ub.uni-koeln.de/id/eprint/64227 |
https://orcid.org/0000-0001-5300-3705Downloads
Downloads per month over past year
Export
Actions (login required)
 |
View Item |