Jcf. Pujol et R. Poli, EVOLVING THE TOPOLOGY AND THE WEIGHTS OF NEURAL NETWORKS USING A DUALREPRESENTATION, Applied intelligence, 8(1), 1998, pp. 73-84
Evolutionary computation is a class of global search techniques based
on the learning process of a population of potential solutions to a gi
ven problem, that has been successfully applied to a variety of proble
ms. In this paper a new approach to the construction of neural network
s based on evolutionary computation is presented. A linear chromosome
combined to a graph representation of the network are used by genetic
operators, which allow the evolution of the architecture and the weigh
ts simultaneously without the need of local weight optimization. This
paper describes the approach, the operators and reports results of the
application of this technique to several binary classification proble
ms.