Sairam Sundaresan
Sairam Sundaresan

@DSaience

8 Tweets 172 reads Sep 29, 2022
What is the fastest way to get good at Machine Learning? πŸš€
Meticulously studying other's code.
Here are 5 of the best git repositories to significantly accelerate your growth in ML 🧡
#ML #Python #MachineLearning
Vision Transformers
Phil Wang, a.k.a lucidrains has one of the best transformer implementations out there. The code is easy to read, and beautifully structured.
If attention is all you need, lucidrains code is all you need:
github.com
Your Own Deep Learning Library
The entire fast.ai library was built in Jupyter notebooks. You can learn how to construct a state of the art library yourself by studying these notebooks here:
github.com
Autograd from Scratch
As Deep learning practitioners, we take autograd for granted and just focus on modeling. Andrej Karpathy's micrograd repository is a lesson in brevity of code and clarity of function.
Learn how autograd works under the hood here:
github.com
That's a wrap!
If you enjoyed this thread:
1. Follow me @DSaience for more on Machine learning, computer vision and being a productive practitioner
2. RT the tweet below to share this thread with your audience
Want to level up your Machine Learning skills efficiently & sustainably?
Subscribe to my weekly newsletter, Gradient Ascent to level up your machine learning skills and become a productive practitioner here:
newsletter.artofsaience.com

Loading suggestions...