Machine Learning 101
Introduction to machine learning. Gives a brief description of what machine learning is and how models can be trained by optimising parameters. This tutorial is written for Onfido.
How to implement a neural network
5 (+2) parts tutorial on how to implement a simple neural network model. The tutorial starts with a simple model and builds up to a handwritten digit classifier. The math is explained along the way together with Python code examples. You can download the different parts and run them yourself with IPython notebook.
How to implement a recurrent neural network
2 part tutorial on how to implement a recurrent neural network. The tutorial explains the basics of backpropagation through time and discusses some of the difficulties of training recurrent networks. You can download the different parts and run them yourself with IPython notebook.
Higher-Level APIs in TensorFlow
How to use TensorFlow's Estimator, Experiment and Dataset APIs to train models.