Solving Differential Equation with Constrained Multilayer Feedforward Network
For researchers using neural networks to solve differential equations, this method improves accuracy by integrating boundary conditions directly into the model, addressing a known limitation.
The paper introduces a neural network framework for solving differential equations where boundary conditions are directly embedded as constraints, enabling unconstrained optimization and achieving higher accuracy than previous neural solvers.
In this paper, we present a novel framework to solve differential equations based on multilayer feedforward network. Previous works indicate that solvers based on neural network have low accuracy due to that the boundary conditions are not satisfied accurately. The boundary condition is now inserted directly into the model as boundary term, and the model is a combination of a boundary term and a multilayer feedforward network with its weight function. As the boundary condition becomes predefined constraintion in the model itself, the neural network is trained as an unconstrained optimization problem. This leads to both ease of training and high accuracy. Due to universal convergency of multilayer feedforward networks, the new method is a general approach in solving different types of differential equations. Numerical examples solving ODEs and PDEs with Dirichlet boundary condition are presented and discussed.