Abstract | ||
---|---|---|
Music composition with algorithms inspired by nature has led to the creation of systems that compose music with rich characteristics. Nevertheless, the complexity imposed by unsupervised algorithms may arguably be considered as undesired, especially when considering the composition of rhythms. This work examines the composition of rhythms through L and Finite L-systems (FL-systems) and presents an interpretation from grammatical to rhythmic entities that expresses the repetitiveness and diversity of the output of these systems. Furthermore, we utilize a supervised training scheme that uses Genetic Algorithms (GA) to evolve the rules of L and FL-systems, so that they may compose rhythms with certain characteristics. Simple rhythmic indicators are introduced that describe the density, pauses, self similarity, symmetry and syncopation of rhythms. With fitness evaluations based on these indicators we assess the performance of L and FL-systems and present results that indicate the superiority of the FL-system in terms of adaptability to certain rhythmic tasks. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2330784.2330855 | GECCO (Companion) |
Keywords | Field | DocType |
rhythmic sequence,genetic algorithms,simple rhythmic indicator,finite l-systems,certain rhythmic task,genetic evolution,present result,fitness evaluation,compose music,rhythmic entity,certain characteristic,music composition,genetic algorithm,rhythm,genetics,l systems | Adaptability,Genetic Evolution,Computer science,Musical composition,Syncopation,Artificial intelligence,Supervised training,Rhythm,Self-similarity,Genetic algorithm,Machine learning | Conference |
Citations | PageRank | References |
4 | 0.55 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Maximos A. Kaliakatsos-Papakostas | 1 | 67 | 13.26 |
Andreas Floros | 2 | 80 | 16.12 |
Nikolaos Kanellopoulos | 3 | 12 | 2.15 |
M.N. Vrahatis | 4 | 1740 | 151.65 |