Full-access lesson
The Chain Rule
> Chapter 1's two-layer network — `sigmoid(linear(relu(linear(x))))` — has been sitting in this book since page one. This chapter finally differentiates it, weight by weight, using the one rule that makes backpropagation possible.
The complete curriculum
All 12 volumes, companion resources, interviews, and architecture reviews.
Executable engineering practice
Subscriber-only Python, Java, TypeScript, and SQL labs in the isolated runner.