7 articles.
What changes when you describe a problem as variables, domains and constraints instead of as a black box: commutativity that shrinks the tree for free, propagation that proves branches hopeless before searching them, and a measurement showing the most famous ordering heuristic does nothing on its own.
Turning a problem into a state space and letting an algorithm walk it: what completeness and optimality actually cost, why memory rather than time defeats breadth-first search, and the two conditions on a heuristic that make A* provably optimal.
Layers as parameterised transformations, the forward pass, and why depth and non-linearity are not optional: a proof that no single linear layer can compute XOR, and a two-layer network that does, worked entirely by hand.
How text becomes numbers a model can train on: building a vocabulary, why byte pair encoding never needs an unknown token, the embedding layer as a lookup that is provably one-hot times a matrix, and why position has to be added back in by hand.
Build probability from the ground up: possible worlds, the sample space, the two basic axioms, and the addition and multiplication rules, each derived rather than asserted, with worked numeric examples.
The setup behind every predictive model: estimating an unknown function f from data, the split between reducible and irreducible error, and why prediction and inference pull in different directions.
Derive the least-squares coefficients by differentiating the residual sum of squares, then work a complete five-observation fit by hand: coefficients, fitted values, residuals, RSS, and R-squared, each verified numerically.