talk
The spelled-out intro to neural networks and backpropagation: building micrograd
Andrej Karpathy · 17 recommenders · 16 months
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 Hacker News readers recommend it: 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.
Machine learning & deep learningPython, Ruby & scripting languages#micrograd#autograd#backpropagation#neural networks#python#andrej karpathy
“It's especially useful because he explains the why and provides intuitive explanations instead of just talking about the what and how.”
View the original HN discussion
