Using AI as a Creative Tool: Music & Art Generation with Magenta
I'll discuss Magenta (g.co/magenta), an open source research project exploring the role of AI as a tool in the creative process. I'll discuss some recent breakthroughs in machine learning that make this work possible -- don't worry... no expertise required! --- and will offer some demos of AI music and art. I'll also talk about the implications of using AI for creative purposes, relating AI to previous technologies like oil paints in tubes, the film camera, and the electric guitar. These older technologies made some things easier for artists (for example, paints in tubes allowed painters to work outside). More importantly, these tools enabled artists to take their art in interesting new directions. Will AI provide us with something as transformational as a film camera or an electric guitar? The signs are promising, but I think it's too soon to tell.
- Art has always relied on technology, from oil paint to the film camera to the drum machine
- AI provides us with exciting new tools for making art and music
- We see an opportunity not only to extend artistic expression with AI but also to offer new ways to learn to make music and art
I’m a research scientist working on Magenta, a research project exploring the role of machine learning in the process of creating art and music. Primarily this involves developing new deep learning and reinforcement learning algorithms for generating songs, images, drawings, and other materials. But it's also an exploration in building smart tools and interfaces that allow artists and musicians to extend (not replace!) their processes using these models. Started by me in 2016, Magenta now involves several researchers and engineers from the Google Brain team as well as many others collaborating via open source. Aside from Magenta, I'm working on sequence learning models for summarization and text generation as well new ways to improve AI-generated content based on user feedback.