Program Overview

Mathematics for Machine Learning and Artificial Intelligence (MATH0114)

Key Information

The module is part of the Faculty of Mathematical and Physical Sciences, with the Mathematics department being the teaching department. It has a credit value of 15. Restrictions apply, as this module is normally taken by students in year 3 of a mathematics degree at level 6 UG, and by students on the MSc in Mathematics at level 6 PG.

Alternative Credit Options

There are no alternative credit options available for this module.

Description

This module introduces students to the theoretical foundations of methods used in Machine Learning and Artificial Intelligence. It covers the mathematical foundations of three learning paradigms:

• Linear regression for supervised learning
• Principal component analysis for unsupervised learning
• Backpropagation for deep learning Additionally, it studies the mathematics behind diffusion models, a notable generative AI method for producing images from text. Besides theoretical aspects, students are exposed to practical implementations of machine learning algorithms through lectures and online tutorials on coding in Python.

Module Deliveries for 2026/27 Academic Year

Intended Teaching Term: Term 2, Postgraduate (FHEQ Level 6)

Teaching and Assessment

• Mode of study: In person
• Methods of assessment:
  • 90% Exam
  • 10% Coursework
• Mark scheme: Numeric Marks

Other Information

• Number of students on module in previous year: 0
• Module leader: Dr Alejandro Diaz De La O

Intended Teaching Term: Term 2, Undergraduate (FHEQ Level 6)

Teaching and Assessment

• Mode of study: In person
• Methods of assessment:
  • 90% Exam
  • 10% Coursework
• Mark scheme: Numeric Marks

Other Information

• Number of students on module in previous year: 103
• Module leader: Dr Alejandro Diaz De La O

Last Updated

This module description was last updated on 10th March 2026.