-
Course code
Qualifications are made up of courses. Some universities call these papers. Each course is numbered using 6 digits.
- 158736
-
Level
The fourth number of the course code shows the level of the course. For example, in course 219206, the fourth number is a 2, so it is a 200-level course (usually studied in the second year of full-time study).
- 700-level
-
Credits
Each course is worth a number of credits. You combine courses (credits) to meet the total number of credits needed for your qualification.
- 15
- Subject
- Information Technology
Course planning information
Expected prior learning
Some understanding of programming and algorithms.
General progression requirements
You may enrol in a postgraduate course (that is a 700-, 800- or 900-level course) if you meet the prerequisites for that course and have been admitted to a qualification which lists the course in its schedule.Learning outcomes
What you will learn. Knowledge, skills and attitudes you’ll be able to show as a result of successfully finishing this course.
- 1 Analyse Machine Learning and Deep Learning methodologies, as well as data preparation, feature engineering, and evaluation techniques, to determine their suitability for different problem domains.
- 2 Implement Deep Learning architectures such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) and Transformers, applying appropriate training strategies and optimisation techniques.
- 3 Apply Large Language Models (LLMs) and other advanced Deep Learning approaches to develop solutions for real-world AI applications.
- 4 Critically assess the implications of ethical, societal and responsible AI principles related to Machine Learning systems when designing AI applications.
Learning outcomes can change before the start of the semester you are studying the course in.
Textbooks needed
There are no set texts for this course.