Inducing Musical Rules with ILP

Previous research in learning sets of rules in a musical context has included a broad spectrum of music domains. Widmer [8] has focused on the task of discovering general rules of expressive classical piano performance from real performance data via inductive machine learning. The performance data used for the study are MIDI recordings of 13 piano sonatas by W.A. Mozart performed by a skilled pianist. In addition to these data, the music score was also coded. When trained on the data the inductive rule learning algorithm discovered a small set of 17 quite simple classification rules [8] that predict a large number of the note-level choices of the pianist.