NetNeg: A Connectionist-Agent Integrated System for Representing Musical Knowledge

D. Gang, C. Goldman, D. Lehmann and J. Rosenschein

The system presented here shows the feasibility of modcling the knowledge involved in a complex musical activity by integrating sub-symbolic and symbolic processes. This research focuses on the question of whether there is any advantage in integrating a neural network together with a distributed artificial intelligence approach within the music domain. The system is designed to perform in real time and to be used for interactive computer music composition or performance. The hybrid approach introduced in this work enables the musician to encode his knowledge and aesthetic taste into different modules. This is done by applying three distinct functions: rules, fuzzy concepts, and learning. As a case study, we began experimenting with first species two-part counterpoint melodies. We have developed a hybrid system composed of a connectionist module and an agent-based module to combine the subsymbolic and symbolic levels to achieve this task. The technique presented here to represent musical knowledge constitutes a new approach for composing polyphonic music.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.