Keele Badge

CSC-20101 - Module Specification
School of Computer Science and Mathematics
Faculty of Natural Sciences

For academic year: 2026/27 Last Updated: 06 April 2026

CSC-20101 - Artificial Intelligence and Machine Learning
Coordinator: Alastair Channon Room: CR035 Tel: +44 1782 7 34270
Lecture Time: See Timetable...
Level: Level 5
Credits: 30
Study Hours: 300
School Office: 01782 733075

Programme/Approved Electives for 2026/27

None

Available as a Free Standing Elective

No

Co-requisites

None

Prerequisites

CSC-10084 - Problem Solving and Computer Programming

Barred Combinations

None

Description for 2026/27


Aims
The aim of the module is to provide students with an introduction to artificial intelligence, including neural networks, deep learning, evolutionary algorithms and neuroevolution. The focus will initially be on understanding the underlying principles, structures, algorithms and capabilities of AI systems, and then on writing programs that use appropriate machine learning software libraries to pre-process data and apply AI to tasks such as text analysis, data analytics and visualisation, computer vision, image processing and pattern recognition.

Intended Learning Outcomes

evaluate the use of artificial intelligence techniques: 2
explain the use of artificial intelligence techniques: 2
apply artificial intelligence concepts: 2
demonstrate appropriate use of techniques for extracting information from data: develop software that uses appropriate AI libraries to create, train and evaluate deep neural networks:

Study hours

30 hours lectures
30 hours practical classes
Independent study, coursework and open book assessment:
60 hours background reading
60 hours revision of lecture materials
90 hours preparation and revision of practical classes materials
28 hours coursework preparation
2 hours exam

School Rules

None

Description of Module Assessment

1: Assignment weighted 50%
AI software development and recorded screencast
Students will be required to write a program or programs to create, train and evaluate a deep neural network for a given or chosen task; experiment with model architecture and parameter choices, commenting intelligently on their effect on results; and evaluate their results in the context of the capabilities and limitations of deep neural networks. Each student will submit their program code (equivalent to a 3000 word report) together with a "recorded screencast" or "live demo" (equivalent to a 2000 word report) of them using their software to train and evaluate their deep neural network; vary model architecture and parameters, commenting on results; and discuss their results in the context of the capabilities and limitations of deep neural networks.

2: Exam weighted 50%
2-hour unseen examination
2-hour unseen examination. Students answer two of three questions: Q1 is a compulsory question; students choose between Q2 and Q3.

The University undertakes a continuous review of its teaching and research provision to ensure programmes are of a high quality and changes may be made to modules where it is necessary and reasonable to do so. Please be aware that minor changes to modules, such as a change to an individual assessment, can occur up until enrolment, although we endeavour to give you as much notice as possible of any changes. Details about the circumstance in which changes are made to programmes can be found in the Student Agreement, available at: https://www.keele.ac.uk/legalgovernancecompliance/governance/actcharterstatutesordinancesandregulations/studenttermsconditions/

Last Updated: 06 April 2026