I. Geometry of data spaces
Proximity in data spaces
Distances and similarities
Data structures and algorithms for proximity search
II. The basic primitives
Simple summary statistics
Online unsupervised learning
Basics of clustering
Informative projections
Singular value decomposition
III. Modeling the distribution of data
Fitting probability distributions to data
Maximum entropy distribution modeling
Bayesian inference
Multivariate Gaussians and Gaussian processes
Bayes nets and autoregressive models
Markov random fields and energy-based models
Sampling by random walk
IV. Embeddings
Embeddings of distance and similarity structure
Autoencoders