Yet another introduction to Neural Networks

In this notebook, I will explain how to implement a neural network from scratch and use the version of MNIST dataset that is provided within Scikit-Learn for testing. I will specificallty illustrate the use of Python classes to define layers in the network as objects. Each layer object has forward and backward propagation methods which leads to compact, easily readable code. In writing this tutorial, I've had inspiration from Peter Roelants' page. After loading the data, we divide it into three parts, training, validation and testing sets.