hwacowboy.blogg.se

The aim of the module is to introduce key statistical techniques for learning from data, mostly within the framework of Bayesian statistics. Assessment detailsĢ hr written examination or alternative assessment Educational aims & objectives

Approximate inference: variational methods, expectation-propagation, sampling methods.Ī good working knowledge of Multivariate Calculus, Probability and Statistics II and Linear Algebra or equivalent.Linear classification, Gaussian process classification, Laplace approximation, link to Support Vector Machines, sparsity.

Learning of input-output relations: linear regression, evidence approximation for optimizing hyperparameters, Gaussian processes.Learning of probability distributions: maximum likelihood and Bayesian learning of Gaussian distributions, conjugate priors, Gaussian mixtures, expectation-maximization approach.Review of basic notions of probability.A good working knowledge of Multivariate Calculus, Probability and Statistics II and Linear Algebra or equivalent.