Title: Evolutionary single hidden-layer feed forward networks

Authors: Youssef Safi; Abdelaziz Bouroumi

Addresses: Information Processing Laboratory, Ben Msik Faculty of Sciences, Hassan II Mohammedia-Casablanca University, BP.7955 Sidi Othmane, Casablanca 20702, Morocco ' Information Processing Laboratory, Ben Msik Faculty of Sciences, Hassan II Mohammedia-Casablanca University, BP.7955 Sidi Othmane, Casablanca 20702, Morocco

Abstract: We propose an evolutionary method for optimising both the architecture and the synaptic weights of single hidden-layer feed forward neural networks. Based on evolutionary strategies, this method uses new genetic operators of mutation and recombination in order to evolve a population of candidate solutions in the form of neural networks with different architectures. Experimental results are presented to demonstrate the effectiveness of the proposed method in both classification and prediction problems. These results concern six well-known benchmark problems and are compared to those produced for the same problems by three other methods.

Keywords: artificial neural networks; evolutionary algorithms; classification; prediction; machine learning; evolutionary ANNs; feedforward neural networks; evolutionary strategies; Proben1; supervised learning; multilayer perceptron; MLP; ANN optimisation.

DOI: 10.1504/IJICA.2014.066497

International Journal of Innovative Computing and Applications, 2014 Vol.6 No.2, pp.73 - 86

Received: 14 Apr 2014
Accepted: 01 Oct 2014

Published online: 31 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article