Artificial Intelligence

This module introduces you to fundamental machine learning concepts and techniques mainly from a practical, problem-solving perspective. You’ll learn the foundations of predictive tasks and will explore contemporary techniques for predictive modelling and model evaluation. Introduction to different paradigms of machine learning, linear prediction, regression, maximum likelihood, Bayesian ML, linear classification, logistic regression, Naïve Bayes, decision trees and fuzzy systems.

This module builds on Machine Learning Concepts and introduces further, fundamental techniques in supervised and unsupervised learning, as well as in model evaluation, interpretation, and explanation.

This module explores a range of fundamental algorithms and data structures used to solve a number of computational challenges fundamental to the study of computer science disciplines. You'll learn to consider and discuss algorithm complexity and efficiency through practical implementation.

The module will cover concepts and implementation of key search strategies for problem solving in AI, including uninformed search, heuristics and informed search, search for optimisation, adversarial search, stochastic search, genetic algorithms. Furthermore, the module will consider the application, testing and cross-comparison of these implementations in the context of simple one and two-player games.

This module covers the principal mathematical and statistical topics required to pursue further study in the areas of data science and machine learning.

This module covers both theoretical and practical aspects involved in the design and development of Knowledge Representation and Reasoning (KBS). We’ll cover a brief overview of AI and the position of KBS within it, KBS architectures, the importance of search within KBS, propositional and predicate logics, inference strategies, knowledge representation, uncertain reasoning, explanation, expert systems and distributed AI. 

The module will provide an overview of the core areas in robotics including motion planning; state estimation, localisation, and mapping; vision and language for robotics; robotics platforms and Robotic Operating System (ROS).

Furthermore, different branches of robotics will be introduced such as industrial robots and collaborative robots (cobots), neuro-robotics, evolutionary, swarm robotics, social robotics and human-robot interaction. You’ll explore the role of the Embodiment in Socially Interactive Robots and their interaction with humans and why should embodied robots be used instead of simpler and more economical virtual agents. 

In this module you’ll learn and discuss issues including, AI and social impact, trust, explainability, accountability, bias and risk within using AI systems, data governance and DPIA systems, case studies of autonomous and intelligence systems.

In conjunction with a member of academic staff, you'll undertake an individual research project. While the project must be related to your degree, you may choose or invent the precise topic yourself. As part of the research, you'll be expected to design, implement and evaluate a substantial piece of software or other product, which will embody the research question of your topic. You'll document the research by writing a dissertation, covering the background of your topic, the approach you have adopted and its relation to previous work, the results you obtained and the conclusions which can be drawn from them.