Despite major advancements in artificial intelligence (AI) in a number of sectors, like the AI that beat the world champion at Go, its progress in the creative realm has yet to be fully proven. Once in awhile, news about an AI getting shortlisted for a literary prize will come up (no, seriously), but so far, achievements and milestones in the arts are few and far between.
Alas, we don’t have a fantastic robot-Picasso just yet, but Google is working to fix that.
They just announced Magenta—a research project that will explore how AI can be used to produce art.
According to a member of the research team, the group will first study what algorithms will be able to generate music. From there, the team hopes to move to video and other visual arts.
You can see the AI music work in the video below:
“There’s a couple of things that got me wanting to form Magenta, and one of them was seeing the completely, frankly, astonishing improvements in the state of the art [of creative deep learning]. And I wanted to demystify this a little bit,” Douglas Eck, a researcher on the project said during a panel at Moogfest, a music and technology festival.
Magenta will be launched on June 1st.
Inspired by Google DeepDream, the Magenta project hopes to anchor this study on deep learning models open-source on top of TensorFlow—Google’s open source AI platform.
They also hope to produce an app that could put the spotlight on visual art produced from Magenta and allow the public to gauge whether the kind of art it produces does indeed have aesthetic and artistic value.