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