Module 06-32167 (2019)

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.

• 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

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

Students must have A-Level Mathematics or equivalent

3 hrs/week of lectures

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

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

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

1. Introduction to Neural Networks and their History
2. Biological Neurons and Neural Networks, Artificial Neurons
3. Networks of Artificial Neurons, Single Layer Perceptrons
4. Learning and Generalization in Single Layer Perceptrons
5. Hebbian Learning, Gradient Descent Learning
6. The Generalized Delta Rule, Practical Considerations
7. Learning in Multi-Layer Perceptrons - Back-Propagation
8. Learning with Momentum, Conjugate Gradient Learning
9. Bias and Variance - Under-Fitting and Over-Fitting
10. Improving Generalization
11. Applications of Multi-Layer Perceptrons
12. Recurrent Neural Networks
13. Radial Basis Function Networks: Introduction
14. Radial Basis Function Networks: Algorithms
15. Radial Basis Function Networks: Applications
16. Self Organizing Maps: Fundamentals
17. Self Organizing Maps: Properties and Applications
18. Learning Vector Quantization
19. Committee Machines
20. Model Selection and Evolutionary Optimization