Evolution of topology and weights of neural networks using semi genetic operators

Abstract AR

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 presen،.

A ؛ineax ' representation of the network is used by genetic operators, which allow the evolution of the architecture and weights ' ال،هم the need of local weights optimization.

This paper describes the approach, the operators and reports resuits of the application of this technique to several binary classification problems.