Research Online


Goldsmiths - University of London

NN Music: Improvising with a 'Living' Computer

Young, Michael W.. 2007. 'NN Music: Improvising with a 'Living' Computer'. In: International Computer Music Conference. San Francisco 2007. [Conference or Workshop Item]

Text (Publisher's version. Copyright the author.)

Download (167kB) | Preview
Text (Poster. Copyright the author.)

Download (412kB) | Preview

Abstract or Description

This paper proposes attributes of a living computer music, the product of a live algorithm. It illustrates how these attributes can inform creative design with reference to a real-time system for solo performer-machine collaboration, Neural Network Music, and the PQƒ framework proposed for live algorithms. Improvisation is treated as a classification problem at a high level of musical behaviour which can be measured statistically and train a multilayer perceptron neural network. Network outputs shape a stochastic-based synthesis engine. Mappings are covertly assigned, revisited by both player and machine as a performance develops. As the timing and choice of mapping is unknown, both participants are invited to learn and adapt to a responsive sonic environment which is created afresh on each performance. This offers a novel real-time application of feed-forward neural networks and a challenging, creative technological platform for freely improvised music.

Item Type:

Conference or Workshop Item (Paper)

Additional Information:

Originally published in Proceedings of the conference, ISBN 0-973192-5-1. Copyright remains with the author.


improvised music; neural networks

Departments, Centres and Research Units:




Event Location:

San Francisco

Date range:


Item ID:


Date Deposited:

21 Apr 2008 17:21

Last Modified:

01 Aug 2018 01:47


View statistics for this item...

Edit Record Edit Record (login required)