Magenta is a Google Brain project to ask and answer the questions, “Can we use machine learning to create compelling art and music? If so, how? If not, why not?”
Magenta encompasses two goals. It’s first a research project to advance the state-of-the-art in music, video, image and text generation. Second, Magenta is building a community of artists, coders, and machine learning researchers. Magenta is an open source infrastructure for making art and music based on Tensor Flow, the machine learning library inspired on how the brain works that is used across many Google platforms, from email to speech recognition. Magenta already has a set of tools for working with data formats like MIDI and is expanding to platforms that help artists to connect with machine learning models.
Team members of this project will present it at Sónar+D.