ML Resources
The sheer volume of courses and textbooks about Machine learning might seem overwhelming, but getting started is easier than you think. I first became interested during my second year of undergrad, which I spent in lockdown building ML projects. Here are some resources that I’ve personally used and found incredibly helpful.
- 3Blue1Brown’s Linear Algebra series
- Optional, but a personal favorite cause it’s a really intuitive introduction to matrix math we’ll be using.
- Machine learning by Andrew Ng
- Beginner friendly introduction to Machine Learning that’ll help you build a solid base.
- An Introduction to Statistical Learning with Python
- I used this more as a reference textbook and imo it’s best to have a decent understanding of statistics and linear algebra before you start reading.
What next?
I liked Deep Learning so I pretty much switched gears and learnt more about Neural Networks. My personal favourites are:
- 3Blue1Brown’s Neural Networks series
- Explains the math about backpropagation and gradient descent visually which is super intuitive.
- PyTorch for Deep Learning & Machine Learning by Daniel Bourke
- When in doubt, code it out!
- Neural Networks: Zero to Hero by Andrej Karpathy
- Combines theory, practical and also details mathematical implementations.
What next pt.2?
Making projects and reading research papers will help you understand the latest advancements in the field. Try implementing the code from these papers to see how it works in practice.
All the best!