Recent advances in the last decades in cognitive sciences, neurobiology
and computer sciences make artificial neural networks (ANN) more pliable in
musical applications. This connexionist paradigm, which is dramatically
different to traditionnal computing, requires a variety of approaches, from the
more factual (biology, physics, computing) to the more abstract (sciences of
cognition, sociology, artificial intelligence).
This text presents some aspects of the Neuromuse project developped at CIRM. In the following notes, we will present some experiences in using self- organizing maps (SOM) to generate meaningful musical sequences, with real-time interfaces, in MaxMSP and Jitter...