One more “curated” list of Python and Machine Learning Courses
“Where can I learn Python/Machine Learning?”
As several friends and online strangers keep asking me
“Where can I learn Python/Machine Learning”,
I put together this syllabus — yes, one more “curated” list on the internet!
Some of the stuff goes back to my thesis days in 2016. If it worked for me, there’s a solid chance it could do wonders for you too!
Notes to readers:
NOTE 1: You’ll notice that certain courses and lectures date back several years. Even though libraries and tools evolve over time and newer versions of some of the listed courses exist (e.g. CS231n), the fundamental principles remain consistent. This is why universities still employ decades-old textbooks.
This list offers a solid foundation, rendering the most recent course iterations unnecessary for acquiring knowledge. (+ Andrej Karpathy presented much of CS231n during the Winter 2016 semester; his intuition and insightful comments are timeless).
NOTE 2: I’ve assigned every item listed here to a rather subjective difficulty scale.
NOTE 3: In the realm of Machine Learning, I distinguis between two distinct groups: the practitioners and those who delve deeper the intricacies of the field.
Practitioners: hands-on wizards who apply ML techniques to real-world problems
Research-minded learners: curious minds who peek behind the curtain delving into the theoretical foundations — If you’re the type of person who’s screaming “whyyy” or “hooow” in frustration, follow this symbol (🔷)!
🟩 (easy)
🟨 🟨
🟧 🟧 🟧
🟥 🟥 🟥 🟥 (as hard as it gets)
🔷 (Deeper theoretical understanding)
NOTE 4: No NLP stuff listed — your “tokens” are no good here 😐
Introduction to Python
🟩 Microsoft Developer — Python for Beginners [link]
Covers: setting up Visual Studio Code, prints, conditions, data structures, loops, functions, virtual environments, decorators
🟩 Microsoft Developer — More Python for Beginners [link]
Covers: formatting and linting, lambdas, classes, working with files
🟩 Microsoft Developer — Even More Python for Beginners: Data Tools [link]
Covers: Jupyter Notebooks, Anaconda, pandas, scikit-learn, numpy, matplotlib
Further useful sources
The sites below host tutorials on different topics and libraries that you can explore on your path to becoming a Pythonista.
https://calmcode.io/
Amazing project!!! I learned some tqdm tricks from here!https://realpython.com/
One more awesome platform full of Python guides and tutorials!
f-strings are a must!
Machine Learning
🟨 🔷 Machine Learning Foundations [link]
Covers: mathematics for ML; really helpful if you want to complete Stanford CS229, CORNELL CS4780, Stanford CS231n
🟨 Machine learning in Python with scikit-learn [link]
🟧 Supervised Machine Learning: Regression and Classification [link]
🟧 🔷 Stanford CS229: Machine Learning Full Course taught by Andrew Ng
Deep Learning
🟧 🔷 CS231n: Deep Learning for Computer Vision [link]
CS231n Winter 2016
YouTube playlist [link]
Course page [link]
(feel free to check out more recent iterations of this course; however, 2016 is a classic!)Yes you should understand backprop [link]
Vintage blog post written by Andrej Karpathy on the value of making students calculate backpropagation from scratch.
