CS5019: Artificial Intelligence (Special Subject)
This module is offered in 2026-27.
Aims
The aims of this module are:
- To introduce the fundamental theoretical frameworks and computational techniques used to enable autonomous decision-making.
- To develop proficiency in representing complex environments and applying algorithmic and data-driven techniques to optimise agent behaviour.
Learning Outcomes
On successful completion of this module, the student should:
- Understand the methods used to guide agents toward goal-directed behaviour in both known and uncertain environments.
- Be able to model dynamic environments and evaluate how different abstraction levels influence performance.
- Understand the computational constraints of decision-making and how various approximations and learning methods are used to achieve scalability.
Syllabus
- An introduction to the principles of automated decision-making.
- Techniques for encoding states, actions, and rewards across diverse domains.
- Exploration of algorithms for navigating state spaces, ranging from exhaustive search to iterative refinement.
- Learning-based decision making: an overview of techniques that utilise feedback and experience to derive policies and optimise performance in complex and uncertain environments.
Compulsory Elements
This module has no compulsory elements beyond those common to all modules (mark of 4 in each assessment component).
Module Delivery
- TBD