lecture · intro · evergreen
The spelled-out intro to neural networks and backpropagation: building micrograd
Andrej Karpathy · Aug 16, 2022 · 2h 25m
What this video covers
Andrej Karpathy's first Neural Networks: Zero to Hero lecture, which builds micrograd, a tiny autograd engine, from scratch in Python. It explains backpropagation and neural network training step by step, assuming only basic Python and some high-school calculus.
Why it surfaced in Hacker News
HN treats it as the best starting point for really understanding backprop and neural nets, because Karpathy explains the why with intuition and builds everything in code.
- 17
- distinct recommenders
- 16
- recommendation months
- 10
- strong recommendations
Recommendation context
Short excerpts from positive mentions. Open the source to read the full Hacker News discussion.
“I recommend watching Andrej Karpathy's recent videos on backprop and neural nets. Makes it really simple and intuitive.”
“Andrej has a brilliant series of videos on youtube where he explores the basics of neural nets right up to transformer architecture through code.”
“The one that really hit it home for me was the first video on MicroGrad”