Music composition is a domain well-suited for evolutionary reinforcement learning. Instead of applying explicit composition rules, a neural network is used to generate melodies. An evolutionary algorithm is used to find a neural network that maximizes the chance of generating good melodies. Composition rules on tonality and rhythm are used as a fitness function for the evolution. We observe that the model learns to generate melodies according to these rules with interesting variations.

PDF, PS

In Proceedings of the {INNS-IEEE} International Joint Conference on Neural Networks, 2241-2246, Piscataway, NJ, 2001. IEEE.

@InProceedings{chen:ijcnn01, title={Creating Melodies With Evolving Recurrent Neural Networks}, author={Chun-Chi J. Chen and Risto Miikkulainen}, booktitle={Proceedings of the {INNS-IEEE} International Joint Conference on Neural Networks}, address={Piscataway, NJ}, publisher={IEEE}, pages={2241-2246}, url="http://nn.cs.utexas.edu/?chen:ijcnn01", year={2001} }