Automatic music generation using evolutionary algorithms and neural networks
Ali Cagatay Yiiksel, Mehmet Melih Karci, A. Şima Uyar · 2011
A music generation system using evolutionary algorithms and recurrent neural networks as the fitness evaluator is developed. The music generation process is fully automatic and requires no human interaction during the evolution phase. A data set which contains samples from The Beatles is used to train the neural network. Software for experimental purposes is developed and executed with different data sets and parameter settings. As a result, it is observed that using an evolutionary approach, the software can successfully generate simple musical ideas.