Artificial neural networks generation using grammatical evolution

In this paper an automatic artificial neural network generation method is described and evaluated. The proposed method generates the architecture of the network by means of grammatical evolution and uses back propagation algorithm for training it. In order to evaluate the performance of the method, a comparison is made against five other methods using a series of classification benchmarks. In the most cases it shows the superiority to the compared methods. In addition to the good experimental results, the ease of use is another advantage of the method since it works with no need of experts.