DSC2006 : Machine Learning and Deep Learning
- Inactive for Year: 2026/27
- Module Leader(s): Professor Jaume Bacardit
- Lecturer: Professor Chris Oates, Dr Stephen McGough
- Owning School: Computing
- Teaching Location: Newcastle City Campus
Semesters
Your programme is made up of credits, the total differs on programme to programme.
| Semester 2 Credit Value: | 20 |
| ECTS Credits: | 10.0 |
| European Credit Transfer System | |
Aims
This module develops your understanding of machine learning and deep learning approaches for analysing real-world data. You will study methods for prediction, classification, and pattern discovery, alongside approaches for selecting, evaluating, and comparing models in different computational contexts. The emphasis is on developing effective modelling workflows, understanding how data representation and preparation influence model performance, and interpreting results critically to support informed decision making and responsible application in practice.
Outline Of Syllabus
Topics covered by this module include:
Paradigms of machine learning and data-driven modelling
Knowledge representation and feature representation approaches
Standard machine learning algorithms for prediction and classification
Ensemble methods and model combination techniques
Multi-layer perceptrons and neural network architectures
Backpropagation, loss functions, optimisation methods, and training workflows
Data preparation, preprocessing, and feature engineering
Deep learning approaches, including convolutional neural networks, recurrent neural networks, and transformer architectures
Teaching Methods
Teaching Activities
| Category | Activity | Number | Length | Student Hours | Comment |
|---|---|---|---|---|---|
| Guided Independent Study | Assessment preparation and completion | 1 | 20:00 | 20:00 | Preparation for practical sessions that include in-lab assessment |
| Guided Independent Study | Assessment preparation and completion | 1 | 35:00 | 35:00 | Preparation and completion of summative report |
| Structured Guided Learning | Lecture materials | 20 | 1:00 | 20:00 | Reading through lecture materials – preparing / follow up |
| Guided Independent Study | Assessment preparation and completion | 1 | 62:00 | 62:00 | Independent study and revision for final exam |
| Guided Independent Study | Assessment preparation and completion | 1 | 2:00 | 2:00 | Completion of exam |
| Scheduled Learning And Teaching Activities | Lecture | 21 | 1:00 | 21:00 | Lectures |
| Guided Independent Study | Directed research and reading | 20 | 1:00 | 20:00 | Wider reading as per provided reading list |
| Scheduled Learning And Teaching Activities | Practical | 20 | 1:00 | 20:00 | Supervised practical sessions focused on hands on implementation |
| Total | 200:00 |
Teaching Rationale And Relationship
This module includes an encounter with the leading edge of research.
Assessment Methods
The format of resits will be determined by the Board of Examiners
Exams
| Description | Length | Semester | When Set | Percentage | Comment |
|---|---|---|---|---|---|
| Written Examination | 120 | 2 | A | 40 | N/A |
Other Assessment
| Description | Semester | When Set | Percentage | Comment |
|---|---|---|---|---|
| Report | 2 | M | 30 | 2h in-lab assessment on Machine Learning |
| Report | 2 | M | 30 | Practical report on the experimental application of machine learning and deep learning algorithms (maximum 2000 words) |
Assessment Rationale And Relationship
The written examination assesses students’ understanding of the principles, methods, and behaviour of machine learning and deep learning approaches. The examination evaluates students’ ability to reason about model selection, representation, optimisation, performance, and suitability for different computational and real-world scenarios. The examination particularly assesses conceptual understanding of machine learning and deep learning algorithms and their appropriate application within practical contexts. (MLO1, MLO3, MLO5)
The machine learning coursework provides students with the opportunity to apply machine learning techniques within a supervised practical setting. Students will prepare data, implement models, evaluate performance, and interpret outputs within a structured computational workflow. The assessment evaluates students’ ability to apply and analyse machine learning approaches using real-world datasets. (MLO1, MLO2, MLO3, MLO4)
The deep learning coursework assesses students’ ability to apply deep learning approaches within an experimental and analytical context. Students will design and evaluate experiments, implement learning models, analyse outcomes, and communicate findings through a structured technical report. The assessment emphasises reproducibility, interpretation, and critical evaluation of model behaviour and performance. (MLO1, MLO2, MLO3, MLO4, MLO5)
The assessment structure supports the development of both conceptual understanding and applied modelling skills, enabling students to develop confidence in the implementation, evaluation, and interpretation of machine learning and deep learning approaches within practical computational settings.
Alternative assessment:
For students with a Student Support Plan (SSP) who have alternative assessment as a reasonable adjustment and/or students with supported Personal Extenuating Circumstances (PEC), it may be necessary to set an alternative assessment as presented below. Due to the professional requirements of some programmes, alternative assessments may not be available even where students are eligible.
An oral examination may be offered as an alternative to the written examination where appropriate. The oral examination would comprise a 15-minute prepared topic followed by 15 minutes of questions from the overall module syllabus. Alternative arrangements for coursework assessments may include an equivalent time-constrained or take-home assessment where appropriate.
Reading Lists
Timetable
- Timetable Website: www.ncl.ac.uk/timetable/
- DSC2006's Timetable