About This Course
This course is designed for experienced programmers who want to understand large language models through implementation, not just theory. By building working examples yourself, you develop deep understanding of what’s actually happening inside modern AI systems.
You’ll progress from first-principles building blocks — starting with a tiny autograd engine — through neural networks, sequence models, and attention, up to the transformer architecture that powers modern LLMs. Every concept is grounded in code you write yourself.
Prerequisites: programming experience, mathematical maturity (calculus + linear algebra, OK if rusty). No prior ML knowledge required.
Course Structure
Seven modules, each building on the last:
Learning Path
The modules are designed to be followed sequentially — concepts compound. Rough phase breakdown:
| Phase | Modules | Focus |
|---|---|---|
| Foundations | 1 | Autograd, gradients, a tiny neural net from scratch |
| Neural networks | 2 | Deep learning fundamentals |
| Sequence models | 3–4 | CNNs, RNNs, LSTMs |
| Attention & transformers | 5–6 | Attention mechanisms, transformer architecture |
| Beyond | 7 | To be determined |
Download
The original course documents are available as a single archive: course.zip