Explores the influence of complexity on ergodic properties of symbolic systems, presenting the Curtis-Hedlund-Lyndon Theorem and constructions of minimal subshifts.
Covers the k-Nearest-Neighbor classifier, hand-written digit recognition, multi-class k-NN, data reduction, applications, graph construction, limitations, and the curse of dimensionality.
Explores learning latent models in graphical structures, focusing on scenarios with incomplete samples and introducing the notion of distance among variables.