Artificial neural networks for solving ordinary and partial differential equations
- 1 January 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 9 (5), 987-1000
- https://doi.org/10.1109/72.712178
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 equationsKeywords
This publication has 9 references indexed in Scilit:
- Merlin-3.0 A multidimensional optimization environmentComputer Physics Communications, 1998
- The Merlin control language for strategic optimizationComputer Physics Communications, 1998
- Artificial neural network methods in quantum mechanicsComputer Physics Communications, 1997
- VLSI implementation of locally connected neural network for solving partial differential equationsIEEE Transactions on Circuits and Systems I: Regular Papers, 1996
- Solution of nonlinear ordinary differential equations by feedforward neural networksMathematical and Computer Modelling, 1994
- The numerical solution of linear ordinary differential equations by feedforward neural networksMathematical and Computer Modelling, 1994
- Parallel finite-element computation of 3D flowsComputer, 1993
- Neural algorithm for solving differential equationsJournal of Computational Physics, 1990
- Structured trainable networks for matrix algebraPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990