Genetic Algorithm Utilising Neural Network Fitness Evaluation for Musical Composition
The aim of the paper is to propose a means by which neural network fitness evaluation can be applied to a genetic algorithm (GA), and an application of this system to musical rhythm composition. An adaptive resonance theory (ART) neural network is trained using binary information representing classification patterns. By comparing new genetically derived individuals to clustered data, a measure of fitness of the new patterns is determined; the patterns of higher fitness values then being used in successive generations to further improve the overall population fitness. A proposed application for this system is described — a genetic composer that utilises clustered representations of rhythm styles to interactively generate rhythm patterns to the user’s general stylistic requirements.
KeywordsFitness Evaluation Adaptive Resonance Theory Rhythm Pattern Vigilance Test Musical Instrument Digital Interface
Unable to display preview. Download preview PDF.
- J.A. Biles. Genjam: A genetic algorithm for generating jazz solos. In Proceedings of the International Computer Music Conference, 1994.Google Scholar
- J.A. Biles, P.G. Anderson, and L.W. Loggi. Neural network fitness functions for a musical iga. Technical report, Rochester Institute of Technology, 1996. http://www.it.rit.edu/jab/SOC096/SOCO.html.Google Scholar
- D.E. Goldberg. Genetic Algorithms in Search, Optimisation and Machine Learning. Addison-Wesley, 1989.Google Scholar
- D. Horowitz. Generating rhythms with genetic algorithms. In Proceedings of the 1994 International Computer Music Conference, pages 142–143, 1994.Google Scholar
- R.A. McIntyre. Bach in a box: The evolution of four-part baroque harmony using the genetic algorithm. In Proceedings of the IEEE Conference on Evolutionary Computation, pages 852–857, 1994.Google Scholar
- A. Nigrin. Neural Networks for Pattern Recognition. MIT Press, 1993.Google Scholar
- G. Schneider, J. Schuchhardt, and P. Wrede. Amino acid sequence analysis and design by artificial neural network and simulated molecular evolution-an evaluation. Endocytobiosis and Cell Research, 11(1):1–18, 1995.Google Scholar