Google’s first project for Magenta was to create a song via machine learning.
Advertisement
The Magenta project runs on top of Google’s open-source AI engine, TensorFlow. The project will also be an open-source only.
This melody is not the first time Silicon Valley has experimented with using AI to make moves into the world of art and culture.
“All machine learning generated music that I know of…suffers from this big problem that we don’t understand how to get this long structure in-the storytelling is missing”, Eck said.
“To start, Magenta is being developed by a small team of researchers from the Google Brain team”. Here’s the first piece of music from Google’s machine-learning system.
As The Verge reports, the melody was created through a “trained neural network, provided with just four notes up front”, while the drums and orchestration “weren’t generated by the algorithm, but added for emphasis”.
Second, Magenta is an attempt to build a community of artists, coders, and machine learning researchers.
Ultimately, Google doesn’t just want the technology to produce “optimal” art based on what it learns from samples. It should feel like there’s a distinct personality to a song or video.
Google has also published a new blog post to talk in length about the objective of the project and offerings that the tech giant’s artistic venture may have in the near future.
Advertisement
Long term goal of Magenta is to advance the state of the machine-generated art. Then build a community of artists around it. Artists and musicians draw our attention to one thing at the expense of another. “Look at the history of creative tools”. As they mention in their blog post: “Surely Rickenbacker and Gibson didn’t have Jimi Hendrix or St. Vincent in mind”. “For example, we want to make it super simple to play music along with a Magenta performance model”.
