Introduction

What this course covers and how to read it

This is a from-scratch course on how AI actually works, structured like a docs site rather than a textbook. Each lesson builds on the last:

  1. History & Landscape — how the field got here
  2. ML Fundamentals — learning as optimization
  3. Probability & Statistics Foundations — the math loss functions are built on
  4. Neural Networks & Backprop — the algorithm behind training
  5. Tooling & The Dev Stack — languages, frameworks, what you'd actually touch
  6. Computer Vision — convolutions and CNNs
  7. Attention & Transformers — the architecture behind modern AI
  8. Generative Models — GANs, VAEs, diffusion — generating new content
  9. LLMs — tokenization, pretraining, fine-tuning, RLHF
  10. Reinforcement Learning — learning from reward, the mechanism behind RLHF
  11. Inference & Serving — what happens when you hit "send"
  12. Evaluation & Benchmarks — how models are actually scored
  13. Prompt Engineering — shaping behavior for free, no training involved
  14. RAG & Vector Databases — giving a model information it wasn't trained on
  15. Agents & Tool Use — giving a model the ability to act
  16. AI Security — prompt injection, jailbreaks, and defending a deployed system from misuse
  17. Applied & Agentic Systems — how the patterns above combine

Who this is for

You should be comfortable with basic programming and high-school math (functions, vectors, derivatives at an intuitive level). No prior ML background is assumed — each lesson introduces its own vocabulary before using it.

How to read it

Lessons are meant to be read in order — later ones assume the vocabulary and intuition built in earlier ones.

Three things to know about the format:

  • Technical terms link to the reference, a glossary of short standalone definitions. Follow them when a word is new; skip them when it isn't.
  • Interactive widgets let you manipulate the thing being described — drag a learning rate around, step through backprop, watch attention weights change.
  • Deep dives are collapsed by default. Anything marked Under the hood contains the formal math and edge cases. The main text is complete without them, so ignore them on a first pass and open them on a second. The toggle at the top of each lesson opens them all at once.

On this page