GANN system to optimize both topology and neural weights of a feedforward neural network

An interesting approach to improve the quality of the artificial neural network architectures included into a large spectrum of applications, is to use the GANN (Genetic Algorithm Neural Network) system concept. Consequently, a specific genetic technique which simultaneously optimizes both topology and neural weights of a feedforward neural network is described. Finally, to confirm the broached theoretical aspects, a real training database was also used.