Machine Learning for Visual Computing
Program Overview
Machine Learning for Visual Computing (COMP0169)
Key Information
The module is part of the Faculty of Engineering Sciences, with the Computer Science department being the teaching department. It has a credit value of 15. The module is available for undergraduate students (FHEQ Level 6) on BSc Computer Science, MEng Computer Science, and MEng Mathematical Computation programs. For postgraduate students (FHEQ Level 7), it is available on MSc Computer Graphics, Vision and Imaging, and MRes Artificial Intelligence Enabled Healthcare.
Alternative Credit Options
There are no alternative credit options available for this module.
Description
Aims
The module aims to equip students with knowledge of how to apply AI to problems from the creative industry, familiarity with basic ML-based algorithms and data structures to process digital media, ability to deal with large-scale data and training of machine intelligence, knowing rephrasing of existing concepts from digital media with tools from AI, and awareness of the difficulty of computed results and artistic freedom.
Intended Learning Outcomes
On successful completion of the module, a student will be able to:
- Formulate the diversity of image analysis and synthesis tasks as a machine learning process.
- Understand theoretical and practical concepts allowing image processing and generation to become learnable and have a basic understanding of how to execute that learning.
Indicative Content
Creative industries such as print, feature films, music, fabrication, or interactive media increasingly make use of multiple machine learning-driven tools. This module enables students to contribute to a new shift of paradigm, where such tools become increasingly intelligent of the content being designed and the users designing them. The module covers an applied background of machine learning and focuses on data structures particularly relevant for creative content such as images and video, and on learnable algorithms that allow machines to process them intelligently, such as convolutional neural networks.
The following topics are indicative of what the module will typically cover:
- Basic regression: Ability to explain basic (1D) data with a linear model and to make predictions.
- Understanding of linearity and non-linearity: Participants will be able to judge if a linear or nonlinear model is adequate and how important non-linearity is for Visual Computing.
- Classification: Ability to formalize a problem as classification and code a simple classifier.
- Neural networks: Students should be able to code up a simple perceptron from scratch and manipulate its parameters.
- Audio/2D/3D images and pixel processing: Load and store images/3D data, audio in the coding environment.
- Tunable image filters; convolutional neural networks: Participants will learn how to execute convolutions on images and how to set up their environment to optimize the parameters of the convolutions.
- 3D meshes and point clouds: Students will learn how to load irregular data into their environment and process them as well as learn tunable filters for them.
- Ambiguity and style: Students will be explained that under some conditions, multiple solutions are valid, and that it can be adequate to report any of these.
- Generative modelling: Introduction to the concept of a generative model, which takes simple parameters in low dimensions and maps them to complex objects in millions of dimensions.
- Levels of supervision; Adversarial training: Students will acquire the skill to replace the supervision in the form of pairs that are mapped to each other by a paradigm where only random samples form a target distribution are given.
Requisites
To be eligible to select this module as an optional or elective, a student must be registered on a programme and year of study for which it is formally available.
Module Deliveries for 2026/27 Academic Year
Intended Teaching Term: Term 1, Undergraduate (FHEQ Level 6)
Teaching and Assessment
- Mode of study: In person
- Methods of assessment: 50% Coursework, 50% Viva or oral presentation
- Mark scheme: Numeric Marks
Other Information
- Number of students on module in previous year: 62
- Module leader: Professor Niloy Mitra
Intended Teaching Term: Term 1, Postgraduate (FHEQ Level 7)
Teaching and Assessment
- Mode of study: In person
- Methods of assessment: 50% Coursework, 50% Viva or oral presentation
- Mark scheme: Numeric Marks
Other Information
- Number of students on module in previous year: 37
- Module leader: Professor Niloy Mitra