Utilisation of an adaptive resonance theory neural network as a genetic algorithm fitness evaluator
Anthony Richard Burton, Tanya Vladimirova · 2002
A novel method of genetic algorithm fitness evaluation, using adaptive resonance theory (ART) neural networks, is proposed. It is shown that a genetic algorithm can use an ART network to assign fitness measures. An ARTMAP network is proposed to control the cluster creation process. This fitness evaluation method is to be applied to an artificial musical composition system.