Machine Learning from First Principles

Connor Brereton
16 min readJan 27, 2019
Machine Learning ~ Applied Mathematics



First and foremost machine learning carries with it this connotation that it is extremely complex. While it is mathematically rigorous it is really simple when you break it down into mathematical terms and even more simple to grasp once you see a real world example of how it is used all the time on people like you and I. My goal is to teach anyone that has a basic understanding of algebra how this crazy stuff works under the hood.

Should I not achieve that goal PLEASE leave a comment so I can answer any questions on this subject!

So let’s dive in…

Where did machine learning come from?

In 1959 while at IBM, Arthur Samuel, an American pioneer in the field of computer gaming and artificial intelligence, coined the term “Machine Learning”. For the next several decades this area of computer science lived in many research labs within corporations and universities until around 2010 when business began to see the value in deep learning and its use in predicting insights within massive datasets that were being generated at corporations, governments, and universities.

It is important to note that many advances within this field are within academia and corporations due to their arguable control over big data according to Stanford GSB.

What do all these buzzwords mean?

The list of buzzwords around artificial intelligence and its sibling — machine learning — seem to be growing everyday, so in order to understand it all let’s visualize where this is all coming from since we are diving into this at a first principle level.