Evolution of Topology and Weights of Neural Networks Using Semi Genetic Operators

Evolutionary computation is a class of global search techniques based on the learning process of a population of potential solutions to a given problem, that has been successfully applied to variety of problems. In this paper a new approach to design neural networks based on evolutionary computation is present. A linear chromosome representation of the network is used by genetic operators, which allow the evolution of the architecture and weights simultaneously without the need of local weights optimization. This paper describes the approach, the operators and reports results of the application of this technique to several binary classification problems.