Design of beta neural systems using differential evolution

Differential evolution (DE) is an exceptionally fast and robust population based search algorithm that is able to locate near optimal solutions to difficult problems. Beside its good convergence properties, DE is very simple to understand and to implement. This paper describes an evolutionary neural network-training algorithm for beta basis function neural networks (BBFNN) using DE. Application to function approximation problems are considered to demonstrate the performance of the BBFNN and of the evolutionary algorithm.