Course
Understand how modern AI actually works by building it: the maths in a few pages, classical models on real tables, a neural network and a transformer in plain numpy, then PyTorch, vision, language models, diffusion, reinforcement learning and the engineering that puts it all into production.
159 chapters in 18 parts 145.7 hours 505 code samples 308 quizzes
18 parts · 159 chapters · 145.7 hours. Each chapter opens with a plain-English lead and ends with the key points and questions to test yourself.
These learning paths take the chapters you need from this course, and from the others, in a short guided route.
Start hereNo background needed
A 13-week program for a complete beginner: Python and data, your first models, how neural networks and language models work, and your first AI agent, with a hands-on lab every week.
13 weeks64 h75 chaptersBeginner
Aspiring ML engineers and analysts
A 14-week program: the maths in a few pages, honest data work, classical models and neural networks you build from scratch, then PyTorch, MLOps and serving, with a lab every week and an end-to-end capstone.
14 weeks67 h91 chaptersAll levels
You use them; now see inside
A 14-week program on how today's models work: convolutions, tokenisers and attention, a small GPT you train, adapters, quantisation and evaluation, then autoencoders, diffusion and reinforcement learning, with a lab every week.
14 weeks70 h69 chaptersAdvanced
This course tells you what was run and what was not. Every Python example marked as runnable (nearly all of them) was executed with numpy, scikit-learn, pandas, SciPy, PyTorch or Gymnasium, and the numbers printed in the text are the ones it produced; the output is shown under the code. A few short illustrative snippets, such as one that downloads pretrained weights, were checked for syntax only and are not marked as runnable. Facts about models, papers, companies and benchmarks come from public information as of the date shown, are hedged with "as of" where they age, and have not all been independently verified against primary sources. Techniques are explained at the level of the ideas; production systems add engineering that a short chapter cannot. If you find a mistake, please report it. Last verified 2026-10-24 against:
Model names, prices and product details are deliberately kept light in the prose: they change too fast. If something here no longer matches a primary source, the source wins, and our corrections page is the place to tell us.