Â鶹´«Ã½

• Inactive for Year: 2026/27

• Module Leader(s): Dr Stephen McGough
• Lecturer: Dr Jere Koskela

• Owning School: Computing
• Teaching Location: Â鶹´«Ã½ City Campus

Semesters

Your programme is made up of credits, the total differs on programme to programme.

Aims

This module gives students a thorough grounding in the foundations of machine learning, deep learning and probabilistic modelling. Machine learning will focus on classic approaches to pattern recognition and predictions. Where pattern recognition is learning the underlying patterns within data and prediction is focused on techniques to learn how to make predictions on the data. These techniques are able to improve with the acquisition of further data. Machine Learning techniques represent the algorithmic foundation for such tasks and involve both statistical modelling techniques and probabilistic reasoning approaches.
This module aims to provide a foundation in the field of Pattern Recognition and an expertise in Machine Learning techniques as a toolkit for automatically analysing (large amounts of) data – be it static data, such as tables, or dynamic data, such as time series and sensor data.

Deep Learning is a sub-field within the area of Machine Learning which has attracted significant interest during recent years most notably because of its ability to outperform humans on many tasks which were previously hard to perform on a computer. Deep Learning is all around us and used daily. If you talk to your phone or a home assistant, it’s Deep Learning which is converting your speech into text. If you search for friends on social media by giving a picture of them, then this is using Deep Learning. Even the adverts you see when surfing the web are likely to have been chosen for you by Deep Learning. Deep Learning is also going to be one of the key technologies for future developments such as self-driving cars and autonomous robots.

This module will introduce students to the area of Deep Learning, the different technologies available along with the myriad of application areas where it can be applied. The aim is to make students fluent in the approach of Deep Learning which will allow them to build up skills that will enable them to apply these skills for applications in companies, academia or the third sector.

Machine and Deep Learning are powerful tools which, like all powerful tools, can be used for good or bad. Hence a running theme within this module will be the ethical use of Machine/Deep Learning along with ensuring that students are aware of the biases which can be present and approaches to minimising such bias. Students will be made aware of good practices for Machine/Deep Learning and how to report their results in a fair and honest manner.

This module gives students a thorough grounding in fundamental probabilistic and statistical modelling, the mathematical manipulation of statistical models and estimators, and practical computation of the same estimators from data sets in simple settings such as regression. It will enable students to confidently pose probabilistic models and use them to carry out statistical learning.

Outline Of Syllabus

This module will cover:
• Paradigms of Machine Learning and Deep Learning.
• Exploratory Data Analysis.
• Experimental Design, data pre-processing and approaches to better training.
• Introduction to Natural Language Processing.
• Interpretability, fairness, and ethics of Machine/Deep Learning.
• Parametric families of statistical models
• The law of large numbers and central limit theorem
• Likelihood, maximum likelihood estimators and their basic properties

Teaching Methods

Teaching Activities

Teaching Rationale And Relationship

Lectures are used for the delivery of theory and methods, illustrated with examples. Problem classes are used to help develop the students’ abilities at applying the theory to solving problems. Practical classes are used to help the students’ ability to apply the methods in practice.

The teaching methods are appropriate to allow students to develop a wide range of skill, from understanding basic concepts and facts to higher-order thinking.

Assessment Methods

The format of resits will be determined by the Board of Examiners

Exams

Other Assessment

Zero Weighted Pass/Fail Assessments

Assessment Rationale And Relationship

A substantial formal unseen examination is appropriate for the assessment of the material in this module. The format of the examination will enable students to reliably demonstrate their own knowledge, understanding and application of learning outcomes.

Examination problems may require a synthesis of concepts and strategies from different sections, while they may have more than one way for solution. The examination time allows the students to test different strategies, work out exam-ples and gather evidence for deciding on an effective strategy, while carefully articulating their ideas and explicitly citing the theory they are using.

The coursework assignments will allow the students to assess their understanding and progress through a formative assessment early in the semester, and then to carry out a similar test later in the module to assess their progress towards the later examination.

The presentation assesses the students’ ability to communicate their findings and approach

In this module, students develop their understanding of the core theory underpinning statistics, and its practical application. Summative assessment of the theory comprises the final written examination and a class-test (which has an additional formative intention).

The zero weighted pass/fail assessment is a mechanism to aid assessment of technical work (which can be challenging to reproduce outside of the learner's computing environment) and as a mechanism to mitigate collusion.

Reading Lists

Timetable

• Timetable Website: