This paper describes recent enhancements to GenJam, a genetic algorithm-based model of a novice jazz musician learning to improvise. After presenting an overview and update of the current interactive version of GenJam, we focus on efforts to augment its human fitness function with a neural network, in an attempt to ease the fitness bottleneck inherent in musical IGAs. Specifically, a cascade correlation technique was used with data taken from populations of musical ideas trained by human mentors interactively. We conclude with a discussion of why this approach failed, and we speculate on approaches that might work.
Date of creation, presentation, or exhibit
Department, Program, or Center
Chester F. Carlson Center for Imaging Science (COS)
Biles, John; Anderson, Peter; and Loggi, Laura, "Neural network fitness functions for a musical IGA" (1996). Accessed from
RIT – Main Campus
Proceedings of the International ICSC Symposium on Intelligent Industrial Automation (IIA'96) and Soft Computing (SOCO'96) 1996 Appears in: Proceedings of the International ICSC Symposium on Intelligent Industrial Automation (IIA'96) and Soft Computing (SOCO'96), March 26-28, Reading, U.K., ICSC Academic Press, ISBN 390-64-5401-0. Complete article also available at: http://www.it.rit.edu/~jab/SOCO96/SOCO.html ISBN: 390-64-5401-0Note: imported from RIT’s Digital Media Library running on DSpace to RIT Scholar Works in February 2014.