Music and Art with ML
summary
Generative music and art experiments use Magenta.js on TensorFlow.js plus simple libs like Tracery.js and platforms like Glitch to make live, remixable tools. Projects include a MIDI-city visual sequencer, Emoji Garden that spawns hundreds of remixes, piano-interfaces and Ableton plugins driven by models such as MusicVAE and Transformers. Models generate believable faces and infinite portraits, installations produce one-off skull paintings that never repeat, and the web demos are lightweight, popular, and actually used in performances.
AI-written summary · about
chapters (10)
- 0:00Start
- 4:02making things is objectively good
- 6:48rules are important for creativity
- 14:18people build serious things so that you can make silly things
- 15:11MAGENTA
- 15:35explore the role of machine learning in the creative process
- 16:15algorithms are functions
- 24:06make music with me
- 30:58code should never hold back art
- 32:09the medium is the message
related talks
28mMusic and AI in the Browser with TensorFlow js and Magenta js
41mMusic and Machine Learning
46mMusic Generation with Magenta: Using Machine Learning in
01h 04mKeynote 3. Interactive generative models for music
21mMusical Deep Neural Networks in the Browser
38mMaking Art with Artificial Intelligence: Artists in Conversation
24mCreating an AI Musician with JavaScript
51mThe Merger of Machine Learning, Music and Programming