After thinking about it for a few weeks, reading some articles and viewing a couple of videos, I decided Machine Learning was something I wanted to learn. Some people don't realise that ML is already part of most the services and apps we use everyday, from searches in Google to recommendations in Amazon or Spotify, spam filters and image recognition (in Google Photos or in autonomous cars) to mention just a few. 

If you know nothing about it, you can read this article which will explain you the basics and, if you really want to go deep into it (like I did) you can enrol in an online course. One of the most recommended courses is the Machine Learning course by the Stanford university which you can find for free in Coursera. It's  instructed by Andrew Ng, who founded Google brain and is one of the most influential persons in ML. Another recommended place to start is the official Google ML site.

Unfortunately for me, the learning curve in both was quite hard as I did not have a background in maths and Machine Learning algorithms rely heavily in Algebra and Statistics. But it's never too late to learn something so I took a step back and decided I wanted to learn the basics, build a foundation in maths and then resume the ML courses.

I started with an Algebra course in Khan Academy which helped me remind most of the basics I already knew from high school but also introduced me to concepts like terms, factors and coefficient, function notation, intervals, domain and range of a function etc... In addition, I noticed there was a Linear Algebra review lecture at the end of the first week of the ML Stanford university course (not sure why they didn't put it at the beginning to be honest...) which focuses in vectors, matrices and how to operate with them. It also explains what are the inverse and transpose and identity matrix.

It took me just a few days to complete these introductions to Algebra and it made me feel like I was back to high school :) After completing them, the lectures and examples of the ML courses are easier to understand and I'm really enjoying them. So if you want to learn ML (or any other thing!) but you feel overwhelm by the amount of new concepts and the complexity of the lectures, take a step back and learn the basics, and get back to it!

Good luck!