Automated composition system based on GA

Researches on computer application to musical creation are actively performed in artificial intelligence. In this paper, we propose a hybrid method that adopts BP neural network for evaluation of emotions in music and genetic algorithm as an appropriate method for nominating creativity. Compared to other GAs used in this field, emotional element is used and combined with some musical rules as fitness function. The experiment results show that our method can yield music which is pleasant to ordinary listeners.