Introduction to Neural Networks - COM00029H

« Back to module search

  • Department: Computer Science
  • Module co-ordinator: Dr. Simon O'Keefe
  • Credit value: 10 credits
  • Credit level: H
  • Academic year of delivery: 2018-19
    • See module specification for other years: 2019-20

Module summary

This module introduces the fundamental concepts of neural networks from a data-oriented perspective - what can simple models of neurons do, what problems can we solve with larger networks, and how do we train and evaluate them using a body of data.

Module will run

Occurrence Teaching cycle
A Spring Term 2018-19 to Summer Term 2018-19

Module aims

Module aim is to introduce the student to the main concepts of feedforward neural networks, from the simplest sum-and-threshold units through to application of networks to real problems. The student will learn about training paradigms for artificial neural networks. The aim is to equip the student to use artificial neural networks appropriately to solve a range of problems and to evaluate the results appropriately.

Module learning outcomes

On completion of this module, students will:

  • Be able to create feedforward neural networks with appropriate architectures
  • Be able to apply appropriate learning and training algorithms
  • Be able to apply neural networks to real problems
  • Be able to analyse the performance of neural networks


Module content

Prerequisite knowledge

Mathematical background in the following will be assumed or introduced:

  • Matrices and vectors
  • Linear algebra
  • Solution of systems of equations
  • Eigenvalues and eigenvectors
  • Partial differentiation
  • Differentiation of scalar functions of vectors and matrices
  • Probability density functions



Task Length % of module mark
INNS Open Assessment
N/A 100

Special assessment rules


Additional assessment information

Formative work is embedded in the module through weekly lab sessions, in which students develop the set of technical skills necessary to undertake the assessment.


Task Length % of module mark
INNS Open Assessment
N/A 100

Module feedback

Feedback to students will be available via:

  • Verbal feedback on practical sessions.
  • Model or outline solutions to exercises, usually 2 weeks after related lab sessions, for self-evaluation.
  • Feedback on practical assessment within 4 term weeks of submission.

Indicative reading

** Haykin, S., Neural Networks:a comprehensive foundation, 3rd ed, Pearson, 2009

* Bishop, C., Neural Networks for Pattern Recognition, OUP, 1995

* Sterrat et al., Principles of Computational Modelling in Neuroscience, OUP, 2011

++ Callan, The Essence of Neural Networks, Prentice Hall, 1999

++ Beale and Jackson, Neural Computing: an introduction, Institute of Physics, 1990

++ Anderson, J.A., An Introduction to Neural Networks, MIT Press, 1995

The information on this page is indicative of the module that is currently on offer. The University is constantly exploring ways to enhance and improve its degree programmes and therefore reserves the right to make variations to the content and method of delivery of modules, and to discontinue modules, if such action is reasonably considered to be necessary by the University. Where appropriate, the University will notify and consult with affected students in advance about any changes that are required in line with the University's policy on the Approval of Modifications to Existing Taught Programmes of Study.