Machine learning algorithms make predictions based on a dataset. If that dataset is a collection of musical notes, the prediction would be a new collection of musical notes. We can consider that prediction the AI’s unique composition. The question is, can an AI really compose music as well as humans can? In this video i’ll go over some really popular models that have been used to generate music, from hidden markov models, to recurrent networks (with their variations), to the modern generative adversarial network. Code, theory, and demos included in this video. Enjoy!
Code for this video:
Please Subscribe! And like. And comment. That’s what keeps me going.
Join us in the Wizards Slack channel:
Sign up for the next course at The School of AI:
And please support me on Patreon: