Skip to main content

Statistical Learning

Overview

Module description

This module introduces you to the techniques of statistical learning. It provides a unified treatment and understanding of the mathematical and statistical basis of a variety of methods for classification, regression and cluster analysis. It also gives you computational experience in applying the relevant methods using a high-level programming language such as R.

indicative module Syllabus

Supervised learning:

  • Linear regression and locally weighted linear regression
  • Generalised linear models for binary and multi-class classification
  • Discriminant analysis
  • Support vector machines
  • Neural networks
  • Learning theory, assessing performance and cross validation
  • Classification and regression trees

Unsupervised learning:

  • Introduction to cluster analysis
  • Hierarchical clustering methods

Learning objectives

By the end of this module, you should:

  • have knowledge and understanding of the methodology, the main techniques and the underpinning mathematical and statistical theory in statistical learning
  • be able to make sensible use of a range of suitable techniques, models and algorithms to elicit useful relations or structure within datasets
  • be able to use advanced mathematical and statistical software to explore datasets
  • be able to incorporate the results of a technical analysis into clearly written report form that may be understood by a non-specialist.