Google’s latest machine-learning project, Magenta, has released its first piece of generated art – a simple 90-second long, four-note piano melody, which was created through a trained neural network. Drums and orchestra were added after the AI’s algorithm, but added for emphasis after the fact.
The Magenta programme has been designed to use Google’s machine-learning systems to create art and music. It’s the first tangible product of Google’s Magenta program. Magenta wants to advance the state of machine-generated art and build a community of artists around it in the long run. The programme will use Google’s open-source artificial intelligence platform TensorFlow to research machine-learning in artistic creation.
It’s not the first time Google has experimented with machine-generated art. The company’s DeepDream algorithm — initially developed to visualize the actions of neural networks — has become a popular image tool in its own right and the basis for a gallery show earlier this year.
Google also developed the Artists and Machine Intelligence program to sponsor further collaborations along the same lines.