School of Computer Science

Module 32167 (2019)

Module description - Neural Computation

The Module Description is a strict subset of the Syllabus Page.

Module Title Neural Computation
School School of Computer Science
Module Code 06-32167
Level 3/H
Member of Staff Per Kristian Lehre Jinming Duan
Semester Semester 1 - 20 credits

3 hrs/week of lectures

Contact Hours: 200 hours Lecture: 33 hours Practical classes/workshops: 22 hours Guided independent study: 145 hours


This module introduces the basic concepts and techniques of neural computation, and its relation to automated learning in computing machines more generally. It covers the main types of formal neuron and their relation to neurobiology, showing how to construct large neural networks and study their learning and generalization abilities in the context of practical applications.


On successful completion of this module, the student should be able to:

  1. understand the relationship between real brains and simple artificial neural network models
  2. describe and explain some of the principal architectures and learning algorithms of neural computation
  3. explain the learning and generalisation aspects of neural computation
  4. demonstrate an understanding of the benefits and limitations of neural-based learning techniques in context of other state-of-the-art methods of automated learning

Sessional: 2 hr examination (80%), continuous assessment (20%)

Supplementary (where allowed): 2 hr examination (100%)