Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
I. E. Lagaris, A. Likas, D. I. Fotiadis
Abstract
We present a method to solve initial and boundary value problems using artificial neural networks. A trial solution of the differential equation is written as a sum of two parts. The first part satisfies the boundary (or initial) conditions and contains no adjustable parameters. The second part is constructed so as not to affect the boundary conditions. This part involves a feedforward neural network, containing adjustable parameters (the weights). Hence by construction the boundary conditions are satisfied and the network is trained to satisfy the differential equation. The applicability of this approach ranges from single ODE's, to systems of coupled ODE's and also to PDE's. In this article we illustrate the method by solving a variety of model problems and present comparisons with finite elements for several cases of partial differential equations.
Create a lesson
Related papers
Physical-state supervision for design-only Gaussian process surrogates of implosion simulations
Chang Liu, Hao Shen, Chuanying Li
Energy-dependent trapping of backscattered helium during magnetron sputtering growth: A molecular dynamics study
Pascal Brault, Anne-Lise Thomann, Alejandro Borroto
Alter-excitons in Altermagnets: Symmetry, Splitting and Dispersion
Yuanfan Xiong, Liangyu Wang, Xuan Wu et al.
All-electron RT-TDDFT with Exact Exchange based on Numeric Atom-centered Orbitals for Condensed Matter
Jianhang Xu, Christopher Shepard, Yosuke Kanai
Polyconvex neural-network surrogates with learned paired directional features for anisotropic hyperelastic homogenization
S. Ares de Parga, A. Cornejo, J. A. Hernández et al.
Parallel Design of a GPU-Resident Semi-Lagrangian Drift-Kinetic Solver on Unstructured Extruded Tokamak Meshes
Mark F. Adams