NEUROGEN, musical composition using genetic algorithms andcooperating neural networks
Gibson, P.M.
Byrne, J.A.
Staffordshire Polytech., Stoke-on-Trent;
This paper appears in: Artificial Neural Networks, 1991., Second International Conference on
Publication Date: 18-20 Nov 1991
On page(s): 309-313
Meeting Date: 11/18/1991 - 11/20/1991
Location: Bournemouth, UK
ISBN: 0-85296-531-1
References Cited: 6
INSPEC Accession Number: 4117802
Current Version Published: 2002-08-06
Abstract
NEUROGEN has been designed with a view to producing small
diatonic, western-type, four-part harmony compositions using the
knowledge extracted from a set of example musical fragments provided by
the user. The aim has been to produce a piece of coherent music that
resembles that typically found in traditional hymns. A set of neural
networks are used to capture the conceptual ideas that build `good'
music and this knowledge is then used to direct a search for the
ultimate composition. Genetic algorithms hold many member states
representing partial musical fragments. The neural networks cooperate to
produce a heuristic value that represents the worth of each of these
musical fragments. This value is then used to evolve better compositions
based on fragments with high fitness values. The use of Neural Networks
as an evaluation function has proved successful in the guidance of
genetic algorithms. This success is evident in the type of composition
produced by NEUROGEN
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
