TLDR; This series is based on the work detecting complex policies in the following real life code story. Code for the series can be found here. In the previous tutorials we outlined our policy classification challenge and showed how we can approach it using the Custom Vision Cognitive Service. This tutorial introduces deep transfer learning as a means to leverage multiple data sources to overcome data scarcity problem. Before we try to build a classifier for our complex policy let's first look at the MNIST dataset to better understand key image classification concepts such as One Hot Encoding, Linear Modeling, Multi Layer Perception, Masking and Convolutions then we will put these concepts together and apply them to our own dataset.