Module 20416 (2006)
Syllabus page 2006/2007
06-20416
Neural Computation
Level 3/H
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 the Introduction to Neural Computation Web-page for module material and further useful links.
Outline
The module introduces the basic concepts and techniques of neural computation and, more generally, automated learning in computing machines. It covers various forms of formal neurons and their relation to neurobiology, showing how to construct larger networks of formal neurons and study their learning and generalisation in the context of practical applications. Finally, neural-based learning techniques are contrasted with other state-of-the-art techniques of automated learning.
Aims
The aims of this module are to:
- Introduce some of the fundamental techniques and principles of neural computation
- Investigate some common neural-based models and their applications
- Present neural network models in the larger context of state-of-the-art techniques of automated learning
Learning Outcomes
| On successful completion of this module, the student should be able to: | Assessed by: | |
| 1 | understand the relationship between real brains and simple artificial neural network models | Examination |
| 2 | describe and explain some of the principal architectures and learning algorithms of neural computation | Examination |
| 3 | explain the learning and generalisation aspects of neural computation | Examination |
| 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 | Examination |
Restrictions, Prerequisites and Corequisites
Restrictions:
May not be taken in conjunction with 06-12412 (Introduction to Neural Computation).
Prerequisites:
None
Co-requisites:
None
Teaching
Teaching Methods:
2 hrs/week of lectures
Contact Hours:
Assessment
- Sessional: 1.5 hr examination (100%)
- Supplementary (where allowed): As the sessional assessment
Recommended Books
| Title | Author(s) | Publisher, Date |
| Neural Networks: A Comprehensive Foundation (Second Edition) | Simon 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 |
| The Elements of Statistical Learning: Data Mining, Inference, and Prediction | Trevor Hastie, Robert Tibshirani, and Jerome Friedman | Springer, 2001 |
Detailed Syllabus
- Brain, biological and formal neurons.
- Learning in formal neurons.
- Layered networks of formal neurons.
- Optimisation algorithms, gradient-based search.
- Learning in layered neural networks.
- Learning and generalisation, bias and variance.
- Recurrent neural networks.
- Learning on temporally dependent data (time series).
- Probabilistic models of data.
- Discriminatory vs. generative approaches to classification.
- Symbiosis between neural networks and probabilistic learning systems.
Last updated: 25 May 2006
Source file: /internal/modules/COMSCI/2006/xml/20416.xml
Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus