Charting Perceptual Spaces with Fuzzy Rules.

Algorithmic music nowadays performs domain specific tasks for which classical algorithms do not offer optimal solutions or require user's expertise. Among these tasks is the extraction of models from data that offer an understanding of the underlying behavior, providing a quick and easy to use way to explore the data for first (sometimes on-the-fly) insights. Learning rules from examples is an approach often used to achieve this goal. However, together with the aforementioned requirements algorithmic composition needs to create new material so that it is perceived as consistent with the material of the data. In addition, the input data sets are usually small because the human is the bottleneck when generating them. In this contribution we present a fuzzy rule induction algorithm focused on generalizing a set of data, complying with the previous requirements, that offers good results for small data sets. For its evaluation -in a field where there are no benchmarks available - data sets obtained during user tests were used. The visual representation offered by the fuzzy chart helps to reduce the cognitive complexity of the devices used in algorithmic music. The results obtained show that this approach is promising for future developments.