EPISODE · May 25, 2018 · 21 MIN
AI for Music Composition
from Siraj Raval
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: https://github.com/llSourcell/AI_For_Music_Composition Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval More learning resources: https://medium.com/artists-and-machine-intelligence/neural-nets-for-generating-music-f46dffac21c0 http://www.asimovinstitute.org/analyzing-deep-learning-tools-music/ https://magenta.tensorflow.org/ https://www.ampermusic.com/ https://blogs.technet.microsoft.com/machinelearning/2017/12/06/music-generation-with-azure-machine-learning/ https://salu133445.github.io/musegan/ Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ Sign up for the next course at The School of AI: https://www.theschool.ai And please support me on Patreon: https://www.patreon.com/user?u=3191693
What this episode covers
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: https://github.com/llSourcell/AI_For_Music_Composition Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval More learning resources: https://medium.com/artists-and-machine-intelligence/neural-nets-for-generating-music-f46dffac21c0 http://www.asimovinstitute.org/analyzing-deep-learning-tools-music/ https://magenta.tensorflow.org/ https://www.ampermusic.com/ https://blogs.technet.microsoft.com/machinelearning/2017/12/06/music-generation-with-azure-machine-learning/ https://salu133445.github.io/musegan/ Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ Sign up for the next course at The School of AI: https://www.theschool.ai And please support me on Patreon: https://www.patreon.com/user?u=3191693
NOW PLAYING
AI for Music Composition
No transcript for this episode yet