COMP0090 Introduction to Deep Learning

This database contains the 2018-19 versions of syllabuses.

Note: Whilst every effort is made to keep the syllabus and assessment records correct, the precise details must be checked with the lecturer(s).

Academic session



Introduction to Deep Learning



Module delivery

1819/A7U/T1/COMP0090 Masters (MEng)

Related deliveries

1819/A7P/T1/COMP0090 Postgraduate

Prior deliveries



Masters (MEng)

FHEQ Level


FHEQ credits



Term 1

Module leader

Barber, David


Barber, David

Module administrator

Ball, Louisa


To have a full understanding of the learning outcomes.

Learning outcomes

On successful completion of the module, a student will be able to:

  1. understand the fundamental principles, theory and approaches for learning with deep neural networks;
  2. understand the main variants of deep learning (such as feedforward and recurrent architectures), and their typical applications;
  3. understand the key concepts, issues and practices when training and modeling with deep architectures;
  4. understand automatic differentation theory and multivariate optimisation;
  5. understand how deep learning fits within the context of other ML approaches and what learning tasks it is considered to be suited and not well suited to perform.

Availability and prerequisites

This module delivery is available for selection on the below-listed programmes. The relevant programme structure will specify whether the module is core, optional, or elective.

In order to be eligible to select this module as optional or elective, where available, students must meet all prerequisite conditions to the satisfaction of the module leader. Places for students taking the module as optional or elective are limited and will be allocated according to the department’s module selection policy.

Programmes on which available:

  • MEng Computer Science (International Programme) (Year 4)
  • MEng Computer Science (Year 4)
  • MEng Mathematical Computation (International Programme) (Year 4)
  • MEng Mathematical Computation (Year 4)


There are no formal prerequisites.


This module will aim to teach students the fundamentals of modern neural networks. It will cover the most common forms of model architectures and primarily the algorithms used to train them. The theory and principles will be presented alongside example applications. The aim is to focus on the core algorithms, ideas and mathematics, rather than any specific implementation framework.

Students will be taught the basics of neural networks, feedforward networks, recurrent networks; and introduced to concepts such as: regularisation, optimisation and hyper-parameter optimization.

An indicative reading list is available via


The module is delivered through a combination of lectures and self-directed learning.


This module delivery is assessed as below:



Weight (%)



Written examination (2 hrs)







In order to pass this Module Delivery, students must:

  • achieve an overall weighted Module mark of at least 50.00%;

AND, when taken as part of MEng Computer Science and MEng Mathematical Computation:

  • achieve a mark of at least 40.00% in any Components of assessment weighed ≥ 30% of the module.

Where a Component comprises multiple Assessment Tasks, the minimum mark applies to the overall component.