Support vector regression method for boundary value problems

This article presents a method to solve boundary value problems using support vector regression and radial basis function network. The boundary is determined by a number of points that belong to it and are closely located, so as to offer a reasonable representation. Two methods are employed: a support vector regression is constructed to have part of effect on the boundary conditions as the basic approximate element and contains adjustable parameters; a radial basis function network is used to account for the exact satisfaction of the boundary conditions. The method was used to solve a two-dimensional partial differential equation and had gained feasible accurate result. This method is completely practical in technology.