Deep Learning without the activation function is just a linear regression model

Neural Networks Made Easy: A Hands-On Introduction Part 1

Deep learning is a type of AI inspired by the human brain, deep learning is made up of neural networks, deep learning is awesome and serious, deep learning is a very advanced model — all of which are true. But every definition and every explanation I read were super superficial. I struggled with understanding what deep learning really was and how it actually works until I came across O'Reilly’s deep learning from scratch (Seth Weidman). Great book by the way. This article is inspired by that book, which I was forced to read by my academic hunk of a father. This is part 1 of my deep learning series; here we introduce the foundation of it all. My job is to make things easy to understand, and I chose the deepest topic this time. Pun intended. Reading this is going to be like a waterfall.

Disclaimer: Please know the basics of a linear regression model before diving in.

1. Function

A function is a rule that takes an input, does something to it and gives an output.

If we put 2, we get 4.
If we put 3, we get 9.