SciELO - Scientific Electronic Library Online

 issue46Constricted Particle Swarm Optimization based Algorithm for Global OptimizationMap Building of Unknown Environment Using L1-norm, Point-to-Point Metric and Evolutionary Computation author indexsubject indexsearch form
Home Pagealphabetic serial listing  

Services on Demand




Related links

  • Have no similar articlesSimilars in SciELO



On-line version ISSN 1870-9044


GARRO, Beatriz A.; SOSSA, Humberto  and  VAZQUEZ, Roberto A.. Automatic Design of Artificial Neural Networks by means of Differential Evolution (DE) Algorithm. Polibits [online]. 2012, n.46, pp.13-27. ISSN 1870-9044.

Artificial Neural Networks (ANN) have been applied in several tasks in the field of Artificial Intelligence. Despite their decline and then resurgence, the ANN design is currently a trial-and-error process, which can stay trapped in bad solutions. In addition, the learning algorithms used, such as back-propagation and other algorithms based in the gradient descent, present a disadvantage: they cannot be used to solve non-continuous and multimodal problems. For this reason, the application of evolutionary algorithms to automatically designing ANNs is proposed. In this research, the Differential Evolution (DE) algorithm inds the best design for the main elements of ANN: the architecture, the set of synaptic weights, and the set of transfer functions. Also two itness functions are used (the mean square error-MSE and the classification error-CER) which involve the validation stage to guarantee a good ANN performance. First, a study of the best parameter coniguration for DE algorithm is conducted. The experimental results show the performance of the proposed methodology to solve pattern classiication problems. Next, a comparison with two classic learning algorithms-gradiant descent and Levenberg-Marquardt-are presented.

Keywords : Differential evolution; evolutionary neural networks; pattern classification.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )


Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License