Free roadmap · updated 2026
The AI & Machine Learning Roadmap
From your first NumPy array to building and shipping LLM apps: 8 phases and 98 topics, in order, with 371 hand-picked free resources. No sign-up, no paywall.
Phases
-
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 · 23 resources -
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 · 56 resources -
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 · 68 resources -
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 · 61 resources -
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 · 60 resources -
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 · 52 resources -
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 · 29 resources -
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 · 22 resources