Learning to Create Jazz Melodies Using Deep Belief Nets

Authors

Greg Bickerman '10, Harvey Mudd College
Sam Bosley, Stanford University
Peter Swire, Brandeis University
Robert M. Keller, Harvey Mudd CollegeFollow

Student Co-author

HMC Undergraduate

Document Type

Conference Proceeding

Department

Computer Science (HMC)

Publication Date

2010

Abstract

We describe an unsupervised learning technique to facilitate automated creation of jazz melodic improvisation over chord sequences. Specifically we demonstrate training an artificial improvisation algorithm based on unsupervised learning using deep belief nets, a form of probabilistic neural network based on restricted Boltzmann machines. We present a musical encoding scheme and specifics of a learning and creational method. Our approach creates novel jazz licks, albeit not yet in real-time. The present work should be regarded as a feasibility study to determine whether such networks could be used at all. We do not claim superiority of this approach for pragmatically creating jazz.

Rights Information

© 2010 University of Coimbra

Terms of Use & License Information

Terms of Use for work posted in Scholarship@Claremont.

Recommended Citation

G. Bickerman, S. Bosley, P. Swire, and R.M. Keller: Learning to Create Jazz Melodies Using Deep Belief Nets, First International Conference on Computational Creativity, Lisbon, Portugal (2010).