Positional Embeddings for Solving PDEs with Evolutional Deep Neural Networks

DOI10.1016/J.JCP.2024.112986MaRDI QIDQ6446517zbMATH OpenFDO

Authors Mariella Kast, Jan S. Hesthaven

Publication date 7 August 2023

Full work available at URL https://doi.org/10.1016/J.JCP.2024.112986

Mathematics Subject Classification ID

Numerical linear algebra (65Fxx) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx) Numerical methods for partial differential equations, boundary value problems (65Nxx)

Recommendations

• Neural Control of Parametric Solutions for High-Dimensional Evolution PDEs
• Deep neural network modeling of unknown partial differential equations in nodal space
• Solving parametric PDE problems with artificial neural networks
• Deep Adaptive Basis Galerkin Method for High-Dimensional Evolution Equations With Oscillatory Solutions
• Learning time-dependent PDEs with a linear and nonlinear separate convolutional neural network

Cited in

(8)

• Fast and scalable computation of shape-morphing nonlinear solutions with application to evolutional neural networks
• Sequential data assimilation for PDEs using shape-morphing solutions
• Multi evolutional deep neural networks (multi-EDNN)
• An efficient stochastic particle method for moderately high-dimensional nonlinear PDEs
• Neural entropy-stable conservative flux form neural networks for learning hyperbolic conservation laws
• Nonlinear model reduction for transport-dominated problems
• Stochastic particle method with birth-death dynamics
• Sequential-in-time training of nonlinear parametrizations for solving time-dependent partial differential equations

This page was built for publication: Positional Embeddings for Solving PDEs with Evolutional Deep Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6446517)