Course Catalogue

Machine Learning (M) COMPSCI5014

  • Academic Session: 2026-27
  • School: School of Computing Science
  • Credits: 10
  • Level: Level 5 (SCQF level 11)
  • Typically Offered: Semester 1
  • Available to Visiting Students: No
  • Collaborative Online International Learning: No
  • Curriculum For Life: No

Short Description

A practical introduction to the foundations of machine learning.

Timetable

3 hours per week.

Requirements of Entry

Mandatory: Working knowledge of mathematics (e.g., matrices, linear spaces and basic geometry, as covered in, for example, Math1RS or Math1RT).

 

Options: Some experience in probability and statistics would be useful but is not essential.

Excluded Courses

Machine Learning (H)

Co-requisites

None

Assessment

Examination 50%, coursework 50%.

Main Assessment In: April/May

Are reassessment opportunities available for all summative assessments? No

It is the default expectation that all courses will offer opportunities for reassessment or deferred assessment. Where it is not possible to offer this in some assessment components, the grade achieved at the first attempt will be counted towards the final course grade, and any exceptions for this course are described below.

[No exceptions]

Course Aims

To present students with an introduction to the general theory of learning from data and to a number of popular Machine Learning methods.  To present students with the practical application of Machine Learning techniques in a variety of domains, including Human Computer Interaction, Information Retrieval, Bioinformatics and Computer Vision and Graphics.

Intended Learning Outcomes of Course

By the end of the course students will be able to:

1. Demonstrate knowledge of the major machine learning application areas in, for example Information Retrieval, Human Computer Interaction, Bioinformatics and Computer Vision & Graphics;

2. Explain the principle of learning from data;

3. Implement and use machine learning algorithms in Python;

4. Apply the main machine learning methods: regression, classification, clustering, probability density estimation and dimensionality reduction;

5. Contrast the strengths and weaknesses of different algorithms for different tasks and datasets;

6. Analyse the benefits and drawbacks of some advanced machine learning approaches, e.g. non-parametric methods, sampling techniques and neural networks.

Minimum Requirement for Award of Credits

No exceptions