Approximation of the objective function: multiquadrics versus neural networks

Abstract

Global optimization in electrical engineering using stochastic methods requires usually a large amount of CPU time to locate the optimum, if the objective 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 functions have been introduced recently. This paper compares the efficiency of both methods, which are applied to a couple of test problems and the results are discussed.

Citation

Ebner, T., Magele, C., Brandstätter, B.R., Luschin, M. and Alotto, P.G. (1999), "Approximation of the objective function: multiquadrics versus neural networks", COMPEL - The international journal for computation and mathematics in electrical and electronic engineering, Vol. 18 No. 3, pp. 250-265. https://doi.org/10.1108/03321649910274766