Module manager: Dr Arash Rabbani
Email: A.rabbani@leeds.ac.uk
Taught: Semester 1 (Sep to Jan) View Timetable
Year running 2026/27
None
COMP2611, COMP3631, COMP3611
This module is not approved as a discovery module
The module will give students hands-on experience with the design, implementation and evaluation of artificial intelligence systems, together with the underpinning theory. The module is divided into a number of topics addressing key areas of artificial intelligence. The topics will reflect foundational concepts in Artificial Intelligence and prepare students to embark on projects within the artificial intelligence domain and further study.
The objective of this module is to provide students with an in-depth understanding of the theoretical foundations and practical applications of Artificial Intelligence. The module equips students with the ability to design, implement, and critically evaluate intelligent systems using contemporary AI techniques, including search, knowledge representation, machine learning, and reasoning under uncertainty. Emphasis is placed on problem formulation, algorithmic decision-making, ethical considerations, and the analysis of real-world AI applications, preparing students for advanced study or professional practice in AI-related domains.
This module provides students with hands-on experience in the design, implementation, and evaluation of artificial intelligence systems, supported by the underlying theoretical principles. It covers both the foundational concepts of classical artificial intelligence, such as search, knowledge representation, reasoning, and planning, and contemporary approaches and trends, including data-driven and learning-based methods. The module is structured around a set of core topics that reflect the breadth and evolution of the field, preparing students to undertake advanced projects in artificial intelligence and to pursue further study or professional practice within the AI domain.
On successful completion of the module students will be able to:
apply knowledge of mathematics, statistics, natural science and engineering principles to the solution of complex problems relating to artificial intelligence . Some of the knowledge will be at the forefront of the subject of study. (C1, M1)
select and apply appropriate computational and analytical techniques to model complex problems, discussing the limitations of the techniques employed. (C3, M3)
select and evaluate technical literature and other sources of information to address complex problems. (C4, M4)
evaluate the environmental and societal impact of solutions to complex problems and minimise adverse impacts. (C7, M7)
identify and analyse ethical concerns and make reasoned ethical choices informed by professional codes of conduct. (C8, M8)
select and use practical laboratory and workshop skills to investigate complex problems and be able to comment on their limitations. (C12, M12. C13, M13)
communicate effectively on complex engineering matters with technical and non-technical audiences, evaluating the effectiveness of the methods used. (C17, M17)
reflect on their level of mastery of subject knowledge and skills and plan for personal development. (C18, M18)
On successful completion of the module students will be able to:
Decompose complex, ill-defined problems into structured computational tasks amenable to artificial intelligence solution.
Select, adapt, and apply appropriate artificial intelligence techniques under constraints such as data quality, performance, and uncertainty.
Design and execute systematic experiments to test hypotheses, interpret results, and inform iterative improvement of technical artificial intelligence solutions.
Communicate technical decisions, assumptions, and results clearly to both specialist and non-specialist audiences using appropriate evidence.
Exercise professional judgement in balancing technical effectiveness with ethical, legal, and societal considerations in system development.
Adversarial Search: Minimax, alpha-beta pruning, basic game-playing agents
Supervised Learning: Linear models, design matrix, decision trees, k-NN, basic evaluation (accuracy, confusion matrix), classification: logistic regression
Machine Learning basics: Supervised vs unsupervised, bias-variance tradeoff, evaluation metrics, overfitting underfitting
Unsupervised Learning: k-means, hierarchical clustering, dimensionality reduction (PCA)
Bayesian Reasoning & Probabilistic Models: Bayes' theorem, Naive Bayes classifier
Bayesian Networks & Markov Models: Conditional independence, Markov models.
Planning: STRIPS, forward/backward planning, planning as search
Reinforcement Learning: MDP, Q-learning, exploration vs exploitation
Search Algorithms: A*, heuristics, pathfinding
Introduction to Robotics Planning, Robotics Learning, Imitation Learning
| Delivery type | Number | Length hours | Student hours |
|---|---|---|---|
| Independent Learning | 0 | 0 | 134 |
| Lecture | 22 | 2 | 44 |
| Practical | 11 | 2 | 22 |
| Private study hours | 0 | ||
| Total Contact hours | 200 | ||
| Total hours (100hr per 10 credits) | 200 | ||
134
Students will receive regular formative feedback through lab classes.
Check the module area in Minerva for your reading list
Last updated: 30/04/2026
Errors, omissions, failed links etc should be notified to the Catalogue Team