Module 12412 (2002)
Syllabus page 2002/2003
06-12412
Introduction to Neural Computation
Level 4/M A
:2.5
John Bullinaria (coordinator)
Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus
The Module Description is a strict subset of this Syllabus Page. (The University module description has not yet been checked against the School's.)
Relevant Links
See Introduction to Neural Computation
Web-page for course material and further useful links.
Outline
Basic Neurobiology; Neural Networks; Single Neuron Models; Single Layer Perceptrons; Multi-Layer Perceptrons; Recurrent Networks; Radial Basis Function networks; Committee machines; Kohonen networks; Applications of neural networks.
Aims
The aims of this module are to:
- introduce some of the fundamental techniques and principles of neural computation
- investigate some common models and their applications
Learning Outcomes
| On successful completion of this module, the student should be able to: | Assessed by: | |
| 1 | understand the relation between real brains and simple artificial neural network models | Examination |
| 2 | describe and explain the most common architectures and learning algorithms for Multi-Layer Perceptrons, Recurrent Networks, Radial-Basis Function Networks, Committee Machines, and Kohonen Self-Organising Maps | Examination |
| 3 | explain the learning and generalisation aspects of neural computation | Examination, assignment |
| 4 | demonstrate an understanding of the implementational issues for common neural network systems | Examination, assignment |
| 5 | demonstrate an understanding of the practical considerations in applying neural computation to real classification, recognition and approximation problems | Examination, assignment |
Restrictions, Prerequisites and Corequisites
Restrictions:
Excluded combination with 06-02360 (Introduction to Neural Networks).
Prerequisites:
None
Co-requisites:
None
Teaching
Teaching Methods:
2 hrs of lectures per week plus labs
Contact Hours:
Assessment
- Supplementary (where allowed): As the sessional assessment
- 2 hr open book examination (70%), continuous assessment by assignment (30%).
Recommended Books
| Title | Author(s) | Publisher, Date |
| Neural Networks: A Comprehensive Foundation | S Haykin | Prentice Hall, 1999 |
| Neural Networks for Pattern Recognition | C M Bishop | Oxford University Press, 1995 |
| An Introduction to Neural Networks | K Gurney | Routledge, 1997 |
| An Introduction to the Theory of Neural Computation | J Hertz, A Krogh & R G Palmer | Addison Wesley, 1991 |
| Neural Networks: A Systematic Introduction | R Rojas | Springer, 1996 |
| The Essence of Neural Networks | R Callan | Prentice Hall Europe, 1999 |
| Introduction to Neural Networks | R Beale & T Jackson | IOP Publishing, 1990 |
Detailed Syllabus
- Introduction to Neural Networks and their History.
- Biological Neurons and Neural Networks, Artificial Neurons.
- Networks of Neurons, Single Layer Perceptrons (SLPs).
- Learning and Generalization in SLPs.
- Hebbian Learning, Gradient Descent Learning.
- The XOR Problem, Linear Seperability, Multi-Layer Perceptrons (MLPs).
- The Back-Propagation Learning Algorithm and its Variations.
- Line Searches and the Conjugate Gradient Learning Algorithm.
- Bias and Variance, Improving Generalization.
- Constructive Algorithms, Pruning Algorithms.
- Applications of Multi-Layer Perceptrons.
- Recurrent Networks.
- Radial-Basis Function Networks.
- Aplications of Radial-Basis Function Networks.
- Committee Machines.
- Kohonen Self-Organising Maps (SOMs).
- Learning Vector Quantisation (LVQ).
- Overview of More Advanced Topics.
- Summary and Review.
Last updated: 19 June 2002
Source file: /internal/modules/COMSCI/2002/xml/12412.xml
Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus