• No products in the cart.


Working in a hands-on learning environment, led by our Machine Learning expert instructor, students will learn about and explore:
Learn how machine learning, deep learning, and reinforcement learning are used in music generation.Generate new content by manipulating the source data using Magenta utilities, and train machine learning models with it.Explore various Magenta projects such as Magenta Studio, MusicVAE, and NSynth.

Course Access

Unlimited Duration

Last Updated

July 29, 2021

Students Enrolled


Total Reviews

Posted by

The importance of machine learning (ML) in art is growing at a rapid pace due to recent advancements in the field, and Magenta is at the forefront of this innovation. With this course, you’ll follow a hands-on approach to using ML models for music generation, learning how to integrate them into an existing music production workflow. Complete with practical examples and explanations of the theoretical background required to understand the underlying technologies, this course is the perfect starting point to begin exploring music generation. The course will help you learn how to use the models in Magenta for generating percussion sequences, monophonic and polyphonic melodies in MIDI, and instrument sounds in raw audio. Through practical examples and in-depth explanations, you’ll understand ML models such as RNNs, VAEs, and GANs. Using this knowledge, you’ll create and train your own models for advanced music generation use cases, along with preparing new datasets. Finally, you’ll get to grips with integrating Magenta with other technologies, such as digital audio workstations (DAWs), and using Magenta.js to distribute music generation apps in the browser..

Course Curriculum

      • Technical requirements 00:00:00
      • Overview of generative art 00:00:00
      • New techniques with machine learning 00:00:00
      • Google’s Magenta and TensorFlow in music generation 00:00:00
      • Installing Magenta and Magenta for GPU 00:00:00
      • Installing the music software and synthesizers 00:00:00
      • Installing the code editing software 00:00:00
      • Generating a basic MIDI file 00:00:00
        • Technical requirements 00:00:00
        • The significance of RNNs in music generation 00:00:00
        • Using the Drums RNN on the command line 00:00:00
        • Using the Drums RNN in Python 00:00:00
        • Technical requirements 00:00:00
        • Generating melodies with the Melody RNN 00:00:00
        • Generating polyphony with the Polyphony RNN and Performance RNN 00:00:00
        • Technical requirements 00:00:00
        • Continuous latent space in VAEs 00:00:00
        • Score transformation with MusicVAE and GrooVAE 00:00:00
        • Understanding TensorFlow code 00:00:00
        • Technical requirements 00:00:00
        • Learning about WaveNet and temporal structures for music 00:00:00
        • Neural audio synthesis with NSynth 00:00:00
        • Using GANSynth as a generative instrument 00:00:00
        • Technical requirements 00:00:00
        • Looking at existing datasets 00:00:00
        • Building a dance music dataset 00:00:00
        • Building a jazz dataset 00:00:00
        • Preparing the data using pipelines 00:00:00
        • Technical requirements 00:00:00
        • Choosing the model and configuration 00:00:00
        • Training and tuning a model 00:00:00
        • Using Google Cloud Platform 00:00:00
          • Technical requirements 00:00:00
          • Introducing Magenta.js and TensorFlow.js 00:00:00
          • Creating a Magenta.js web application 00:00:00
          • Making Magenta.js interact with other apps 00:00:00
          • Technical requirements 00:00:00
          • Sending MIDI to a DAW or synthesizer 00:00:00
          • Looping the generated MIDI 00:00:00
          • Using Magenta as a standalone application with Magenta Studio 00:00:00

        Course Reviews

        Profile Photo
        4 4


        About Instructor

        Course Events


        More Courses by Insturctor

        © 2021 Ernesto.  All rights reserved.