MIT 6.S191 Lab 1: Intro to TensorFlow and Music Generation with RNNs
Part 1: Intro to TensorFlow
TensorFlow is a software library extensively used in machine learning. Here we'll learn how computations are represented and how to define simple neural networks in TensorFlow. TensorFlow uses a high-level API called Keras that provides a powerful, intuitive framework for building and training deep learning models. In this section you will learn the basics of computations in TensorFlow, the Keras API, and TensorFlow's new imperative execution style enabled by Eager.
Part 2: Music Generation with RNNs
In the second portion of the lab, we will play around with building a Recurrent Neural Network (RNN) for music generation. We will be using a "character RNN" to predict the next character of sheet music in ABC notation. Finally, we will sample from this model to generate a brand new music file that has never been heard before!