Foundations
The terms, ideas, and learning paradigms the rest of the field assumes you already understand. Start here if any vocabulary further in feels unfamiliar — these topics are the ground every later chapter stands on.
AI, ML & Deep Learning
The nested-set picture — what each term actually refers to and how they relate.
Supervised, Unsupervised & Reinforcement Learning
The three families of learning, distinguished by what kind of signal the model gets to learn from.
Neural Networks
Layers of weighted sums and nonlinearities — the substrate every modern model is built on.
The Forward Pass
How an input becomes an output, one layer at a time.
Backpropagation & Gradient Descent
The algorithm that turns a wrong prediction into adjusted weights.
The Bitter Lesson & Scale
Why general methods backed by compute keep winning — and why that observation reshapes the field.
Emergence
Capabilities that appear without being trained for — what we know, what we don't, and what to make of it.
Foundation Models
The shift from task-specific to general-purpose, and what it implies for how AI gets built and deployed.