A deep First-Order System Least Squares method for solving elliptic PDEs
Authors:
- Francisco M. BersetcheFBFrancisco M. Bersetche
- Juan Pablo BorthagarayJBJuan Pablo Borthagaray
- 6 December 2022
- journal article
- research article
- Published by Elsevier in Computers & Mathematics with Applications
- Vol. 129, 136-150
Abstract
No abstract availableKeywords
All Related Versions
This publication has 26 references indexed in Scilit:
- A unified deep artificial neural network approach to partial differential equations in complex geometriesNeurocomputing, 2018
- The Deep Ritz Method: A Deep Learning-Based Numerical Algorithm for Solving Variational ProblemsCommunications in Mathematics and Statistics, 2018
- Error bounds for approximations with deep ReLU networksNeural Networks, 2017
- Neural-network methods for boundary value problems with irregular boundariesIEEE Transactions on Neural Networks, 2000
- Artificial neural networks for solving ordinary and partial differential equationsIEEE Transactions on Neural Networks, 1998
- First-Order System Least Squares for Second-Order Partial Differential Equations: Part ISIAM Journal on Numerical Analysis, 1994
- Universal approximation bounds for superpositions of a sigmoidal functionIEEE Transactions on Information Theory, 1993
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Neural algorithm for solving differential equationsJournal of Computational Physics, 1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989