scientific article; zbMATH DE number 1405301
The authors discuss the possibility of using artificial neural networks for the solution of differential equations. They suggest that the approximating functions should be of the form \(A(x)+ F(x, N(x,p))\), where \(A\) satisfies the boundary conditions and \(N\) is a single-output feedforward neural network with parameters \(p\) and \(n\) input units fed with the input vector \(x\). A minimization process is performed to get the best approximation. A similar process can be performed for eigenvalue problems. The ideas are illustrated by a number of examples including the non-local Schrödinger equations and the Henon-Heiles problem. It is suggested that the method can be implemented by digital signal processing. For the entire collection see [Zbl 0927.00051].
- Solving nonlinear differential equations by a neural network method
- Solution of nonlinear ordinary differential equations by feedforward neural networks
- A numerical solution for an initial value problem for ODE using artificial neural network
- Numerical solution of the nonlinear Schrödinger equation by feedforward neural networks
- A numerical method for solving ordinary differential equations by using neural network
- Solution of nonlinear ordinary differential equations by feedforward neural networks
- Basic hardware module for a nonlinear programming algorithm and applications
- Neural network as a function approximator and its application in solving differential equations
- Neural algorithm for solving differential equations
- Solving nonlinear differential equations by a neural network method
- Approximate positive solutions of nonlinear differential equations using neural networks and localization results
- A numerical solution for an initial value problem for ODE using artificial neural network
- Approximation of multi-parametric functions using the differential polynomial neural network
- Inverse problem with respect to domain and artificial neural network algorithm for the solution
- scientific article; zbMATH DE number 2168937 (Why is no real title available?)
- Hermite functional link neural network for solving the Van der Pol-Duffing oscillator equation
- Connectionist learning models for application problems involving differential and integral equations
- An alternative formulation of the differential quadrature method with a neural network perspective
- Numerical solution of the nonlinear Schrödinger equation by feedforward neural networks
- 3D nonparametric neural identification
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4938264)