AWS DeepComposer announces real-time visualizations for in-console model training and improved interactivity in learning capsules

Posted on: May 1, 2020

AWS DeepComposer gives developers a creative way to learn machine learning. With DeepComposer, developers can get hands-on, literally, with a musical keyboard and the latest machine learning techniques to expand their ML skills. Developers can build generative AI models without having to write a single line of code by using the included sample models and training data. To learn the concepts of generative AI algorithms, developers can use the easy-to-consume, bite-size modules known as learning capsules. 

Today, we are excited to announce real-time visualizations for in-console model training and improved interactivity in learning capsules. Using real-time visualizations, developers can understand the performance of the model that they are training by learning about the discriminator and generator loss over time and sampling the graph at various epochs to listen to the output quality. With the added interactivity in the learning capsule, developers explore theoretical concepts mixed with guided hands-on learning to enhance their understanding of machine learning and generative AI.  

Generative AI is one of the exciting recent advancements in artificial intelligence technology because of its ability to create something new. Until now, developers interested in growing skills in this area haven’t had an easy way to get started. With AWS DeepComposer, developers, regardless of their background in ML, can get started with Generative Adversarial Networks (GANs) to learn how to train, and optimize the models to create original music.  

AWS DeepComposer keyboard is available on amazon.com and is priced at $99. The pricing includes the keyboard and a 3-month free trial of AWS DeepComposer services. To activate your free trial, enter your keyboard serial number in the AWS DeepComposer console to link it to your AWS account.  

Learn more about AWS DeepComposer