Andrej Karpathy's Neural Networks: Zero to Hero
karpathy.ai/zero-to-hero.html
A free video lecture series by Andrej Karpathy building neural networks from scratch in pure Python, from backpropagation fundamentals through GPT-level language models.
Why it is useful
The clearest explanation of how neural networks actually work at the implementation level, taught by one of the leading researchers in the field. Building a GPT from scratch in numpy removes the magic from transformer architectures and gives you genuine understanding rather than surface familiarity. Particularly valuable before diving into fine-tuning or building on top of existing models.
More in Learning Resources
Other learning resources you might not have heard of.
- OverTheWireFree security wargames that teach hacking and Linux concepts through levelled challenges you solve over SSH, starting with the beginner-friendly Bandit game.
- MDN Web DocsMozilla's reference documentation for HTML, CSS, and JavaScript — the resource professional web developers keep open in a tab at all times.
- Learn X in Y MinutesA community-written cheat sheet site covering 170+ programming languages and tools in a dense, example-heavy format — showing syntax and idioms from variable declaration to classes in a single scrollable page.
- MathigonInteractive, visual mathematics textbooks covering topics from fractions to chaos theory.
- Boot.devA backend-development learning platform teaching Go, Python, and computer science fundamentals through browser-based coding challenges.
- AnimagraffsEducational site publishing animated technical explainers on engines, aircraft, electronics, infrastructure, vehicles, watches, and other mechanical or scientific systems.