Approximation of the objective function: multiquadrics versus neural networks

Global optimization in electrical engineering using stochastic methods requ ires usually a large amount of CPU time to locate the optimum, if the objec tive function is calculated either with the finite element method (FEM) or the boundary element method (BEM). One approach to reduce the number of FEM or BEM calls using neural networks and another one using multiquadric func tions have been introduced recently. This paper compares the efficiency of both methods, which are applied to a couple of test problems and the result s are discussed.