Title :
Utilisation of an adaptive resonance theory neural network as a genetic algorithm fitness evaluator
Author :
Burton, A.R. ; Vladimirova, T.
Author_Institution :
Sch. of Electron. Eng., Inf. Technol. & Math., Surrey Univ., Guildford, UK
fDate :
29 Jun-4 Jul 1997
Abstract :
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
Keywords :
adaptive signal processing; ART neural network architecture; ARTMAP network; adaptive resonance theory neural network; artificial musical composition system; cluster creation process control; genetic algorithm fitness evaluator; Clustering algorithms; Genetic algorithms; Genetic engineering; Information technology; Mathematics; Neural networks; Optimization methods; Resonance; Rhythm; Subspace constraints;
Conference_Titel :
Information Theory. 1997. Proceedings., 1997 IEEE International Symposium on
Conference_Location :
Ulm
Print_ISBN :
0-7803-3956-8
DOI :
10.1109/ISIT.1997.613124
