A Hierarchical Genetic Algorithm For The Design Of Beta Basis Function Neural Network

1 University 7 November Carthage, Faculty of Sciences of Bizerta, Tunisia [email protected] REGIM: Research Group on Intelligent Machines, University of Sfax, ENIS, Department of Electrical Engineering, BP W 3038, Sfax, Tunisia [email protected] PAMI: Pattern Analysis and Machine Intelligence Labora tory, Systems design Engineering Department University of Waterloo, Waterloo, ON N2L 3G1, Canada [email protected] 4 LASEM: Laboratory of Electromechanical Systems, University of Sfax , ENIS, Department of Mechanical Engineering, BP W 3038, Sfax, Tunisia [email protected] Abstract We propose an evolutionary neural networktraining algorithm for Beta basis function neural networks (BBFNN). Classic training algorithms for neural networks start with a predetermined network structure. Generally the network resulting from learning applied to a predetermined architecture is either insufficient or over-complicated. This paper describes a hierarchical genetic learning model of the BBFNN. In order to examine the performance of the proposed algorithm, they were used for the approximation problems. The results obtained are very satisfactory with respect to the relative error.