Foundations

The mathematics and classic algorithms every later part leans on: vectors and matrices, probability, derivatives and optimization, information theory and search. Each page stays close to what machine learning actually uses, with small examples you can verify by hand.

5 of 5 topics ready, listed in reading order

Linear algebra for machine learningVectors, matrices, projections, eigenvectors and the SVD as they appear in regression and PCA.ReadyProbability and statisticsRandom variables, Bayes' rule, common distributions, estimation, confidence intervals and hypothesis tests.ReadyCalculus and optimizationDerivatives, gradients, the chain rule, Taylor approximation, convexity and gradient descent.ReadyInformation theoryEntropy, cross-entropy, KL divergence and mutual information, and where they show up in trees, losses and compression.ReadySearch algorithmsProblem formulation, BFS, DFS, uniform cost, greedy best-first and A* with admissible heuristics.Ready