Important ☝️

Please keep in mind that this is a personal guide I created for myself to learn these topics outside of my university. Feel free to modify it as you see fit.

After the foundations (after the Deep Learning step), you can choose what to focus on or reorder as you prefer. My own plan is to focus on computer vision first, then move on to NLP and LLMs.

DON’T BE AFRAID OF MATH 🙂‍↔️

For the math parts, we won’t cover EVERY topic in calculus, linear algebra, or statistics. We’ll only focus on the concepts that are actually useful in the ML and DL fields, without going too deep into the rest.

PLEASE TAKE BREAKS 🫠

Learning ML and DL is VERY intense, so don’t forget to step away from the screen now and then. Even short breaks help your brain process and retain information better. Just because I’m writing the weeks by number doesn’t mean you need to follow them consecutively. PLEASE take a few days off whenever you feel like it.

Note About NLP Section 🗣️

By the time you reach NLP in this roadmap, you’ll have already covered a lot of relevant content (LSTMs, GRUs, Attention, Transformers, etc.). So, if you’re not super interested in NLP, you don’t really need to spend weeks on it.

You have two options: Skip it entirely if you just want to focus on other areas. Take the Crash Path, a fast-track version to cover the essentials quickly. Otherwise, go with the detailed path if you want to dive deeper.

Note About Coursera Content 👨‍🏫

Week 1, 2, 3: Python 🐍

Week 4, 5: Data analyzing and Data visualization (Pandas, Numpy, and Matplotlib) 🐼

Week 6, 7, 8, 9: Calculus 📐