Learn the skills, then build something real

Learn AI and machine learning from zero, in order: 8 phases, 98 topics and 371 hand-picked free resources. Tick topics off as you go.

1. Phase 0

   Your toolkit

   Get fast with the tools you will use every day. This phase is short. Do it in the same two weeks as the start of Phase 1.

   6 topics
2. Phase 1

   Math foundations

   The language of ML. You will see matrices as movements of space, gradients as directions, and loss functions as probabilities.

   16 topics
3. Phase 2

   Classical ML, built by you

   Build every classic algorithm yourself in NumPy. After this phase, a library is only a shortcut for something you already understand.

   17 topics
4. Phase 3

   Deep learning foundations

   Build neural networks from a single neuron up. Write backprop by hand first. Then you can trust PyTorch, because you know what it does.

   16 topics
5. Phase 4

   Transformers and LLMs

   Build a small GPT from scratch: tokenizer, attention, training and fine-tuning. This is how modern AI works inside.

   14 topics
6. Phase 5

   AI engineering

   Turn foundation models into real products: retrieval, evaluation, agents and deployment. This is the core of most AI engineer jobs.

   16 topics
7. Phase 6

   Systems and scale

   Make models fast and cheap. Understand what limits speed and memory on a GPU, and how training works across many GPUs.

   9 topics
8. Phase 7

   Generative models and reinforcement learning

   Models that create new data, and models that learn by trial and error. These ideas power image generators, and the reinforcement learning behind RLHF.

   4 topics