The foundational Bayesian ML textbook, rebuilt chapter by chapter as interactive lessons. From polynomial curve fitting to graphical models, with live simulations at every step.
Polynomial curve fitting, probability theory, Bayesian inference, model selection, curse of dimensionality, decision theory, information theory.
Bernoulli, binomial, beta, Gaussian, exponential family, conjugate priors, nonparametric methods.
Basis functions, least squares, bias-variance, Bayesian regression, model evidence.
Fisher's discriminant, perceptron, logistic regression, generative vs discriminative, Laplace approximation.
Feed-forward networks, backpropagation, Hessian, regularization, mixture density networks, Bayesian NNs.
Dual representations, kernel trick, RBF networks, Gaussian processes.
Support vector machines, maximum margin, soft margin, SVR, relevance vector machines.
Bayesian networks, Markov random fields, d-separation, factor graphs, belief propagation.
K-means, Gaussian mixtures, expectation-maximization, ELBO decomposition.
Variational inference, mean field, variational EM, expectation propagation.
Rejection sampling, importance sampling, MCMC, Metropolis-Hastings, Gibbs sampling, HMC.
PCA, probabilistic PCA, kernel PCA, factor analysis, ICA, autoencoders.
Markov models, hidden Markov models, forward-backward, Viterbi, Kalman filters.
Bayesian model averaging, committees, boosting, AdaBoost, decision trees, mixtures of experts.