Advanced2h 26mAndrej Karpathy

The spelled-out intro to neural networks and backpropagation: building micrograd

Name: The spelled-out intro to neural networks and backpropagation: building micrograd
Description: Builds a neural network and backpropagation from raw Python, line by line — the best way to actually understand what's happening under the hood of every ML library.

Builds a neural network and backpropagation from raw Python, line by line — the best way to actually understand what's happening under the hood of every ML library.

Your notes

Saved on this device

Notes save only to this browser, not to an account — clearing your browser data clears them too.

This course is hosted on YouTube by Andrej Karpathy — AIYouth didn't create it, we just organized it and gave you a place to take notes. Watching or crediting this course does not imply any partnership with its creator.

More in Build From Scratch

Let's build GPT: from scratch, in code, spelled out

Andrej Karpathy · 1h 56m