Neural Networks in Python

In this tutorial, we will implement a multi-layered perceptron (a type of a feed-forward neural network) in Python using three different libraries. We'll start off with the most basic example possible, going to more complex and flexible frameworks with the aim of increasing our understanding of how to implement neural networks in Python. Quoting from the scikit-learn documentation [1], "A Multi-layer Perceptron (MLP) is a supervised learning algorithm that learns a function f: Rᵐ Rᵒ by training on a dataset, where m is the number of dimensions for input and o is the number of dimensions for output. Given a set of features X x¹,x²,…,xᵐ, and a target y, it can learn a non-linear function approximator for either classification or regression. It is different from logistic regression, in that between the input and the output layer, there can be one or more non-linear layers, called hidden layers".