In this codelab, you will learn how to build and train a neural network that recognises handwritten digits. Along the way, as you enhance your neural network to achieve 99% accuracy, you will also discover the tools of the trade that deep learning professionals use to train their models efficiently. This codelab uses the MNIST dataset, a collection of 60,000 labeled digits that has kept generations of PhDs busy for almost two decades. You will solve the problem with less than 100 lines of Python / TensorFlow code. What you'll learn - What is a neural network and how to train it - How to build a basic 1-layer neural network using tf.keras - How to add more layers - How to set up a learning rate schedule - How to build convolutional neural networks - How to use regularisation techniques: dropout, batch normalization - What is overfitting What you'll need Just a browser. This workshop can be run entirely with Google Colaboratory.