Anyone can learn machine learning. Your goal, however, determines how you learn machine learning. If your purpose is to abstract away the intricacies and just use the algorithms as it is, then there are many other great resources that will show you how to use libraries and frameworks efficiently.

But if you're like me, you want to understand what's under the hood. This website will help you form a theoretical understanding of the material.

Machine learning is a synergetic field, requiring many prerequisites, especially mathematical maturity.

In order to really dive into machine learning, you must be somewhat comfortable with multivariate calculus, linear algebra, probability, and statistics. No knowledge of the prerequisites, however, shouldn’t impede you. You don’t need to know all of calculus, linear algebra, probability, and statistics. Just small, basic parts of each.

To understand the guides on this website, knowledge of this material is not necessary, but recommended. It’s not about memorizing every little detail of this prerequisite math. It’s more about being comfortable with the core and being able to quickly look up any thing you don’t already know.

The links below can serve as an introduction or brush up your skills in these areas.


Single Variable Calculus
Multivariable Calculus

Linear Algebra

Linear Algebra (Option 1)
Linear Algebra (Option 2)
Linear Algebra (Option 3)
Linear Algebra (Option 4)
Linear Algebra (Option 5)


Probability/Statistics (Option 1)
Probability/Statistics (Option 2)
Probability/Statistics (Option 3)
Probability/Statistics (Option 4)
Probability/Statistics (Option 5)
Probability/Statistics (Option 6)