Project Magenta

Deep learning neural networks have great potential as new tools for creative artists and musicians to use in their work.  Assuming they are packaged in a form that hides the underlying complexity and allows the artist to just focus on being an artist in new and interesting ways.

Project Magenta is an open source research project ongoing at Google. It is exploring the role of machine learning as a tool in the creative process for artists to use.  This includes both making music as well as making visual art. Although they seem to lean more heavily towards music.

There are bunch of different fun Magenta project demos you can check out.

Magenta Studio is a set of music plugins that use machine learning techniques for music generation. You can run them as stand alone applicaation, or as plugins for Ableton Live, which is my personal favorite DAW (digital audio workstation) software.

For developers, they offer a java script api called Majenta.js. For python oriented people, they have a Python Library as well as Colab notebooks you can work with. Colab notebooks are Jupyter notebooks that are hosted by Colab. So Jupyter notebooks hosted by Google in your Google drive account.

And it's all based on Tensorflow, so you can use Python to access all of that as we have discussed in previous posts and will continue to discuss more in future posts. Get up to speed on working with recurrent neural networks for music generation and manipulation.

And because you can look at Jupyter and associated Colab notebooks in your browser, why not take a peek at the Making Music with Magenta notebook.

Comments

Post a Comment

Popular posts from this blog

CycleGAN: a GAN architecture for learning unpaired image to image transformations

Image
 Like the Doublemint Twins touting the joys of Doublemint gum, 2 GANs are surely better than 1 GAN.  Especially if we package them together inside of one meta GAN module.  And this is exactly what the CycleGAN architecture does. Have you ever harbored dark secrets of turning a horse into a zebra?  The CycleGAN was developed to do just that. Learn how to turn a horse into a zebra.  And more. Now right away you can notice a difference between the image to image transformation GAN architectures we've been discussing over the last few posts.  Those last few posts described systems that learn from a database of matched input-output image pairs. And if your goal is to turn an edge representation into a nicely filled in continuous tone image, it's easy to build your database of matched input-output image pairs that your GAN system can then learn off of.  Take a continuous tone image (which will be the output of the database pair entry), then run it through an edge detector algorithm. 
Read more

Pix2Pix: a GAN architecture for image to image transformation

Image
 I thought following up yesterday's TraVelGAN post with a Pix2Pix GAN post would be useful to compare what is going on in the 2 architectures.  Two different approaches to the same problem. I stole this Pix2Pix Overview slide below from an excellent deeplearning.ai GAN course (note that they borrowed it from the original paper) because it gives you a good feel for what is going on inside of the Pix2Pix architecture.    Note how the Generator part is very much like an auto-encoder architecture, but rebuilt using the U-Net architecture features (based on skip-connections) that fastai has been discussing in their courses for several years before it became more widely known to the deep learning community at large  (and which originally came from an obscure medical image segmentation paper) . So the Generator in this Pix2Pix GAN is really pretty sophisticated, consisting of a whole image to image auto-encoder network with U-Net skip connections to generate better image quality at highe
Read more

Smart Fabrics

Image
"What makes smart fabrics revolutionary is that they have the ability to do many things that traditional fabrics cannot, including communicate, transform, conduct energy and even grow."  This is a quote from Rebeccah Pailes-Friedman, who is a professor at Pratt with a research focus on developing wearable technology and smart textiles. Enhancing textiles can be viewed through different lens.  Enhancements can be aesthetic, or performance boosting, or durability boosting. 
Read more