Skip to content

Neural Networks: Zero to Hero

by @product-on-purpose

Andrej Karpathy's video course building neural networks and language models from scratch, from backprop basics to a mini-GPT.

View on GitHub ☆ Save Report
★ 0 saves GitHub ★ 24.2k

Neural Networks: Zero to Hero

Andrej Karpathy's lecture series, with the accompanying notebooks.

What's inside

  • micrograd: backpropagation from first principles
  • makemore: building up to a character-level language model
  • Culminates in building a small GPT
  • Each lecture pairs a long-form video with a Jupyter notebook

License: MIT

Product Artifact Hub — a registry for Product people. GitHub is the source of truth for code. All rights reserved - Wagner Borba (WBTech Studio) © 2026.