Learning and composing of classical music using restricted Boltzmann machines
This work addresses the need for interpretability in AI-generated music, though it is incremental as it applies a simpler model to a known task.
The study tackled the problem of analyzing how machine learning models understand composer styles by using a restricted Boltzmann machine (RBM) trained on J. S. Bach's music, and found that the learned RBM could compose music.
Recently, software has been developed that uses machine learning to mimic the style of a particular composer, such as J. S. Bach. However, since such software often adopts machine learning models with complex structures, it is difficult to analyze how the software understands the characteristics of the composer's music. In this study, we adopted J. S. Bach's music for training of a restricted Boltzmann machine (RBM). Since the structure of RBMs is simple, it allows us to investigate the internal states after learning. We found that the learned RBM is able to compose music.