The Artificial Intelligence Nerd, one of the prized creatures of the world. Not too long ago, these beings were rare and hidden away in university dungeons. But today they flourish. They primp with instinctual grace. They wave their hands impressively to assert their intellectual dominance. They carb-load like overpaid professional athletes. And this makes some sense because they're among the best paid professionals in the world. ~ Bloomberg, in Hello World, S1E14.
AI is like one of the coolest skills to possess on the planet. And one important subset of it is Machine Learning. Machine Learning is cool. But learning Machine Learning is tough, particularly for beginners with not much math background. But Machine Learning doesn't certainly need a Ph.D.
One of the most terrifying nightmares for a Machine Learning beginner is its prerequisites. There are a ton of blogposts that says you must absolutely master Linear Algebra, Calculus, Statistics and Probability, and they are right to some extent.
But to some of us, these things seems absolutely scary at first.
The thing is if you want to take the academic route, you should definitely pursue math seriously. But for those, who just want to build cool shit, you don't really need to master these in your beginner phase. Well, yes, to understand ML algorithms deeply, you need a pretty good understanding of Math. But in the beginning, you should focus more on building stuff if you're into Machine Learning as a developer.
So, here (*drumrolls please!* 🥁) I'm introducing my Linear Algebra for Applied Machine Learning series of tutorials as a part of my Math of Intelligence series.
Why Linear Algebra first? Because Linear Algebra is the mathematics of data, and I believe it is much easier to learn as compared to Calculus.
The thing is Machine Learning practitioners study too much Linear Algebra (and Calculus). They learn far more of the field than is required for Machine Learning. Linear Algebra is a huge field of study and most of which isn't necessary for you to form a deeper understanding of Machine Learning models.
In this series of tutorials, we will only take a look at a specific subset of Linear Algebra, the Linear Algebra that's relevant for Machine Learning.
In this series of tutorials, we'll also take a top-down approach with code snippets in Python and NumPy, rather than the slow and painful bottom-up classical university approach.
When and where will I release the tutorials? I'll start releasing content in the first week of October on this blog site.
What are the prerequisites? Just basic knowledge of Python programming (arrays, if-else conditions, loops, etc.).
Will it cost me anything? Yes, time! It's free of money but it will require your time and undivided attention.
Where to sign up for it? Sign up in the "Subscription" form below with your email address to make sure that the content gets delivered to you. 👇🏻
Update (June, 2019): I'm stacked with work, and haven't really posted more tutorials in the series (apart from Part 1), probably won't be posting it before December this year. Make sure to sign up in the Subscription form below so that I can let you know whenever I post the remaining tutorials. Cheers!