On the Learning Stages of an Intelligent Rhythmic Generator

We are developing RGeme (Rhythmic Meme Generator), an artificial intelligence system for the composition of rhythmic streams inspired by Richard Dawkin's theory of memes. The system is based on intelligent agents that learn from examples and interact by generating rhythms to each other. The system has two broad stages. In the first one, the learning stage, which is the main focus of this paper, Agents are trained with examples of musical pieces in order to evolve a “musical worldview” which consists of a “Style Matrix” of basic rhythmic elements (or "rhythmic memes”). In the production stage, Agents are able to learn from each other's "compositions" and capable of evolving new rhythmic styles by adapting to each other's rhythms. The dynamics of this evolution is studied by analysing the behaviour of the memes logged during the learning and the interaction processes. In this paper we present the learning stage of a simulation of the system that uses rhythmic information taken from music compositions by two Brazilian composers, namely Ernesto Nazareth and Tom Jobim. Only the learning stage is discussed in this paper. The production stage and its connexions with the learning stage will be introduced in a future paper.