Deakin University
Browse

File(s) under permanent embargo

Primal-improv: Towards co-evolutionary musical improvisation

conference contribution
posted on 2017-11-08, 00:00 authored by M Scirea, Peter EklundPeter Eklund, J Togelius, S Risi
© 2017 IEEE. This paper describes a work in progress on co-evolving Artificial Neural Networks (ANNs) for music improvisation. Using this neuro-evolutionary approach the ANNs adapt to the changes in the human player's music as input, while still maintaining some of the structure of the musical piece previously evolved. The system is called Primal-Improv and evolves modules that are composed of two ANNs, one controlling pitch and one controlling rhythm. The results of a quantitative study show that, by only introducing simple rules as fitness functions, the system is able to generate more interesting arrangements than ANNs evolved without a specific objective. The emerging and interesting musical patterns that are produced by the evolved ANNs hint at the promising potential of the system.

History

Pagination

172 - 177

Publisher

IEEE

Location

Colchester, Eng

Place of publication

Pisctaway, N.J.

Start date

2017-09-27

End date

2017-09-29

ISBN-13

9781538630075

Publication classification

EN.1 Other conference paper; X Not reportable

Title of proceedings

CEEC 2017 : 2017 9th Computer Science and Electronic Engineering Conference