Module Catalogue 2024/25

Pre Requisite Comment

N/A

Co Requisite Comment

N/A

Aims

To introduce students to the advanced concepts of machine learning and computer vision, and provide the essential knowledge about the main themes, so that, in the future, they will be able to readily apply their knowledge in industry or research or further enhance it by self-study.

Outline Of Syllabus

Topics will cover contemporary areas subject to changes to follow the advances of ML, Computer Vision, and NLP domains, including but not limited the following areas
Topics will cover, but will not be limited to, some or all of the following areas:
- Machine Learning Theroy
- Based models
- Reinforcement Learning
- Fuzzy Logic
- Auto ML
- Evolutionary Computation
- Image classification
- Segmentation
- Object detection
- Vision transformer
- Federated learning in computer vision
- Generative AI and diffuser
- Deployment of computer vision models and hardware
- Applications - Satellite Imaging, Medical Imaging, Scene Understanding/Classification
- Text Mining
- Natural Language Processing (including LLMs)

Intended Knowledge Outcomes

The students should:
- Be aware of advanced techniques in machine learning and computer vision
- Have a working knowledge of which techniques are useful and appropriate for a particular problem.
- Possess the knowledge of how the different techniques are implemented in common programming frameworks
- Have an appreciation of the ethical obligations required when performing advanced machine learning and computer vision.

Intended Skill Outcomes

The student should
- Be able to understand the advanced concepts behind machine learning and computer vision.
- Discuss and communicate the ability and limitations of machine learning and computer vision approaches.
- Identify the most appropriate machine learning and computer vision approaches for a given problem.
- Be able to use appropriate tools, report results and assess risks/limitations associated with applications of machine learning and computer vision.
- Be able to identify and quantify sources of bias and use appropriate mechanisms to reduce bias.

Teaching Rationale And Relationship

Lectures explain the underlying principles for the module and technologies that support machine learning and computer vision. Lectures are complemented by supervised practical sessions to guide the application of these principles using suitable tools. The practical work builds up experience working with a computational toolset that is used to complete a substantive project working with data from a real-world context.

Assessment Rationale And Relationship

The report tests the students’ ability to apply machine learning and computer vision techniques, using effective tools and methods to solve a real-world challenge.

General Notes

N/A