Improvisation and learning

This article presents a 2-phase computational learning model and application. As a demonstration, a system has been built, called CHIME for Computer Human Interacting Musical Entity. In phase I of training, recurrent back-propagation trains the machine to reproduce 3 jazz melodies. The recurrent network is expanded and is further trained in phase 2 with a reinforcement learning algorithm and a critique produced by a set of basic rules for jazz improvisation. After each phase CHIME can interactively improvise with a human in real time.