Cooperative Coevolution of Generalized Multi-Layer Perceptrons

In this work we present the cooperative coevolution of multi-layer generalized perceptrons. This model is based on the cooperation of different subpopulations of modules, each one being a generalized multi-layered perceptron.In some previous works we have developed a modular cooperative coevolutive model for evolving two hidden-layer perceptrons. This model performs very well but tends to generate quite big networks. In the present paper we show the results of substituting these two-hidden layer perceptrons for generalized multi-layer perceptrons, which allow a more compact representation of networks.The use of the generalized multi-layer perceptrons improved the performance of the evolutionary model in relation to the evolution of other kinds of networks and the networks obtained are much smaller. The comparison proved statistically significant by means of a student's t-test.