Compound Multilayer RBF Network And It’s Application On Numerical Solution Of Partial Differential Equations

This paper presents a kind of algorithm based on the multi-layer RBF network by using the K-mean algorithm and genetic algorithm. Through this two algorithm, the number of cluster and the width of coefficient can be acquired significantly. Through computer simulation of the unit and multivariate function approximation, it shows that the precision by this algorithm is much more higher than the precision by multi layer RBF network..On this basis, we apply this method to solve the numerical solution of partial differential equations, It can solve the defect of low accuracy in the boundary condition. The feasibility of this method can be proved by computer simulation experiment.Finally, this article attempt to apply it to solve the European option pricing model of Black ? Scholes equation. An ideal result is obtained. With the comparision of other methods, the results show that this method has great advantage in calculation precision.