论文信息 - Utilisation of an adaptive resonance theory neural network as a genetic algorithm fitness evaluator

Utilisation of an adaptive resonance theory neural network as a genetic algorithm fitness evaluator

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.

A. R. Burton | T. Vladimirova

[1] Jacek M. Zurada,et al. Introduction to artificial neural systems , 1992 .

[2] Lee Spector,et al. Induction and Recapitulation of Deep Musical Structure , 1995, IJCAI 1995.

[3] Cihan H. Dagli,et al. Genetic neuro-scheduler for job shop scheduling , 1993 .

[4] David E. Goldberg,et al. Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5] D. E. Goldberg,et al. Genetic Algorithms in Search , 1989 .

[6] Stephen Grossberg,et al. ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.