Vibe Coding Discovernn-zero-to-hero
View on GitHubNeural Networks: Zero to Hero
Andrej Karpathy's free video course with Jupyter notebooks that builds neural networks from scratch: micrograd autograd, makemore language models, a GPT transformer, and a BPE tokenizer.
Use Cases
Learn backpropagation by building microgradImplement character-level language models (makemore)Build GPT from scratchUnderstand tokenization by building minBPEStudy BatchNorm, residual connections, AdamUnderstand gradient flow in deep netsLearn language modeling fundamentalsPractice PyTorch tensor operations
Built With
- Language
- Jupyter Notebook
- Frameworks
- PyTorch · NumPy
Tags
neural networks · deep learning · backpropagation · GPT · transformer · tokenizer · PyTorch · micrograd · makemore · educational · video course · Jupyter Notebook · from scratch · language modeling