MS4H03 - Machine Learning 04 Dec 2020 - 31 Aug 2026 | Version 1

Associated Module Information

Module Code: MS4H03
Module Title: Machine Learning
Faculty: Faculty of Computing, Engineering and Science
Faculty Group: Computing and Mathematics
Faculty Sub Group: Maths
Module Leader: Rebecca Peters
Module Team: Stephanie Perkins
First Intended Intake: JAN 2025 Final Year of Intake: 2025
Date Closed:
Credit Value: 10 Credit Level: 7
Language: English
Percentage of Module Taught in Welsh: 0
Equivalent Module:
HECOS codes: 100359 - artificial intelligence 100992 - machine learning 101034 - statistical modelling
HECOS Code Weighting: 25 50 25

Document Version Information

Version 1
Valid From 04 Dec 2020
Valid To 31 Aug 2026

Module Aims

To provide an understanding of the key concepts and techniques associated with machine learning in the context of Data/AI.

To learn how to choose appropriate methods to analyse data, in order to extract information and classify features to inform decision making processes directed at business goals.

Content Summary

This module focuses on combining graduates’ acquired analytical and computing skills and applying them in the desired field of Machine Learning. Topics include, data pre-processing, supervised and unsupervised learning paradigms, regression and classification algorithms.

Learning and Teaching Methods

Activity Type Hours
Lecture 8
Seminar 8
Tutorial 8
Independent Study 40
Directed Study 36
Total Hours Selected 100

Learning Outcomes

# Learning Outcome
LO1 To understand the concepts of machine learning for Data/AI and compare and test a range of classification techniques.
LO2 To classify features of data sources, analysing and interpreting the outputs of machine learning techniques in the context of practical situations in the area of Data/AI.

Module Requisites

N/A

Assessment Criteria

Assessment Category Assessment Type Description Duration Word Count Weight (%) Best of? Pass Mark
Set Exercise - Not Time Constrained (CW) Set Tasks - not-time constrained 1 Within a software package, select and apply a range of algorithms 0 3000 70 No 40
Portfolio Portfolio 1 Practical demonstration of code 0 N/A 30 No 40

Assessment Matrix

Assessment Type Learning Outcomes
LO1 LO2
Set Tasks - not-time constrained 1
Portfolio 1

Reading List

Geron, A. (2017) Hands-On Machine Learning with Scikit-Learn and TensorFlow. O’Reilly.

Russell, S. and Norvig, P. (2013) Artificial Intelligence: A Modern Approach. United Kingdom: Pearson Education.

MacKay, D. J. C. (2003) Information theory, inference, and learning algorithms. 1st edn. Cambridge, UK: Cambridge University Press.

Murphy, K.P. (2012) Machine Learning: a probabilistic perspective. MIT Press.