Computers are well suited to tasks such as data categorization and labeling. More challenging is data “generation”, a problem in which recurrent neural networks (RNNs) and more specifically long short-term memory networks (LSTMs) have made significant progress in the past few years. In this project, I train an RNN on a database of classical sheet music, and use it to generate new sheet music.
Colbert-Pollack, Seth, "RNN monophonic sheet music generation with LilyPond" (2018). IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound. Paper 2.