Description
This module aims to familiarise students with the foundations of machine learning, including its theoretical and algorithmic aspects. The module covers important algorithmic learning paradigms and corresponding machine learning models that are widely used in practice, whilst placing special focus on the mathematical and statistical theories that provide their underpinnings. It is primarily intended for third and fourth year undergraduates and taught postgraduates registered on the degree programmes offered by the Department of Statistical Science (including the MASS programmes). The academic prerequisites for these students (in addition to their compulsory modules) are one of MATH0011 / STAT0040Ìý/ STAT0041 (UG), orÌýSTAT0028Ìý(±Ê³Ò°Õ).
Intended Learning Outcomes
- recognise which particular machine learning methods are applicable for a problem at hand, if any;
- be ableÌýto formulate a problem so that a machine learning solution can be properly assessed;
- have an understandingÌýthe underpinnings of optimisation methods applicable to machine learning tasks;
- recogniseÌýthe direct connections between machine learning methods and statistical modelling;
- be ableÌýto formulate deeper ideas on how to customise models when applying machine learning methods to a novel problem (Level 7 only);
- be ableÌýto provide a more critical appraisal of the suitability of available data to the goals set by a machine learning solution (Level 7 only).
Applications - Machine learning algorithms are widely used in several sectors including healthcare, finance, weather and climate, engineering, and many science and technology domains.
Indicative Content - General principles of learning theory: predictive modelling, model-based learning, data representations, overfitting, cross-validation, empirical risk minimisation, generalisation, notions of Bayesian learning, and probabilistic modelling. Supervised learning: classification and regression, decision trees, kernel machines and neural networks. Unsupervised learning: clustering, dimensionality reduction, latent variable models. Optimisation methods for machine learning. Principles of modelling with nonstandard data: text, images, network data.
Key Texts - Available from .
Module deliveries for 2024/25 academic year
Last updated
This module description was last updated on 19th August 2024.
Ìý