Do you want to learn the maths for machine learning but don't know where to start?

This thread is for you.
🧵👇

The guide that you will see below is based on resources that I came across, and some of my experiences over the past 2 years or so.

I use these resources and they will (hopefully) help you in understanding the theoretical aspects of machine learning very well.
Before diving into maths, I suggest first having solid programming skills in Python.

Read this thread for more details👇

https://t.co/sSN3jdxDwK
These are topics of math you'll have to focus on for machine learning👇

- Trigonometry & Algebra

These are the main pre-requisites for other topics on this list.

(There are other pre-requites but these are the most common)
- Linear Algebra

To manipulate and represent data.

- Calculus

To train and optimize your machine learning model, this is very important.
- Statistics

Make "sense" out of the data you have.

- Probability

Make decisions under uncertainty.
These are some of the resources I recommend for learning these topics 👇
Neural Networks

> A series of videos that go over how neural networks work with approach visual, must watch.

🔗youtu.​be/aircAruvnKk
Seeing Theory
> This website helps you learn statistics and probability in an intuitive way.

🔗seeing-theory.​brown.​edu/basic-probability/index.​html
Gilbert Strang's lectures on Linear Algebra (MIT)

> This is 15 years old but still 100% relevant today!
Despite the fact these lectures are made for freshman college students at MIT, I found it very easy to follow👌

🔗youtube.​com/playlist?list=PL49CF3715CB9EF31D
My Thread on Linear Algebra.

https://t.co/3H7U2HJgTd
The essence of Linear Algebra
> A beautiful playlist of videos which teach you linear algebra through visualisations in an easy to digest manner.

🔗youtube.​com/watch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab
Khan Academy
>You'll find a course on everything here! Khan Academy is the first place I'll go to when I want to learn something.

🔗khanacademy.​org/math
Essence of calculus
> A beautiful series on calculus, makes everything seem super simple.

🔗youtube.​com/watch?v=WUvTyaaNkzM&list=PL0-GT3co4r2wlh6UHTUeQsrf3mlS2lk6x
The math for Machine learning e-book

> This book is for someone who knows quite a decent amount of high school math like trigonometry, calculus, I suggest reading this after having the fundamentals down on khan academy.

🔗mml-book.​github.​io

More from Pratham Prasoon

More from Machine learning

This is a Twitter series on #FoundationsOfML.

❓ Today, I want to start discussing the different types of Machine Learning flavors we can find.

This is a very high-level overview. In later threads, we'll dive deeper into each paradigm... 👇🧵

Last time we talked about how Machine Learning works.

Basically, it's about having some source of experience E for solving a given task T, that allows us to find a program P which is (hopefully) optimal w.r.t. some metric


According to the nature of that experience, we can define different formulations, or flavors, of the learning process.

A useful distinction is whether we have an explicit goal or desired output, which gives rise to the definitions of 1️⃣ Supervised and 2️⃣ Unsupervised Learning 👇

1️⃣ Supervised Learning

In this formulation, the experience E is a collection of input/output pairs, and the task T is defined as a function that produces the right output for any given input.

👉 The underlying assumption is that there is some correlation (or, in general, a computable relation) between the structure of an input and its corresponding output and that it is possible to infer that function or mapping from a sufficiently large number of examples.

You May Also Like