Magenta is a research project analyzing the function of machine learning in creating art and music.
Magenta focuses on developing new deep learning and reinforcement learning algorithms for generating songs, images, drawings and other materials. It also constructs smart tools and interfaces allowing artists and musicians to extend their processes using these models.
The started in 2016 by researchers and engineers from the Google Brain team. It is led by Doug Eck, a research scientist. They use TensorFlow and release their models and tools in open source on GitHub.
Timeline
People
Further reading
A Neural Algorithm of Artistic Style
Leon A. Gatys, Alexander S. Ecker and Matthias Bethge
Academic paper
DRAW: A Recurrent Neural Network For Image Generation
Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende and Daan Wierstra
Academic paper
Generating Sequences With Recurrent Neural Networks
Alex Graves
Academic paper
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
Nicolas Boulange, Yoshua Bengio and Pascal Vincent
Academic paper
Pixel Recurrent Neural Networks
Aaron van den Oord, Nal Kalchbrenner and Koray Kavukcuoglu
Academic paper
Documentaries, videos and podcasts
Magenta: Music and Art Generation (TensorFlow Dev Summit 2017)
15 February 2017
Machine learning
