# Module 06-12412 (2011)

## Introduction to Neural Computation

## Level 4/M

John Bullinaria | Semester 1 | 10 credits |

Co-ordinator: John Bullinaria

Reviewer: Peter Tino

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

### 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:

- Understand the relationship between real brains and simple artificial neural network models
- Describe and explain some of the principal architectures and learning algorithms of neural computation
- Explain the learning and generalisation aspects of neural computation
- Apply neural computation algorithms to specific technical and scientific problems
- 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

### Teaching methods

2 hrs/week of lectures, assigned course work

### Assessment

- Sessional: 1.5 hr examination (80%), continuous assessment (20%)
- Supplementary: 1.5 hr examination (80%), continuous assessment (20%)

### Detailed Syllabus

- Introduction to Neural Networks and their History
- Biological Neurons and Neural Networks, Artificial Neurons
- Networks of Artificial Neurons, Single Layer Perceptrons
- Learning and Generalization in Single Layer Perceptrons
- Hebbian Learning, Gradient Descent Learning
- The Generalized Delta Rule, Practical Considerations
- Learning in Multi-Layer Perceptrons - Back-Propagation
- Learning with Momentum, Conjugate Gradient Learning
- Bias and Variance - Under-Fitting and Over-Fitting
- Improving Generalization
- Applications of MLPs
- Recurrent Neural Networks
- Radial Basis Function Networks: Introduction
- Radial Basis Function Networks: Algorithms
- Radial Basis Function Networks: Applications
- Self Organizing Maps: Fundamentals
- Self Organizing Maps: Algorithms and Applications
- Learning Vector Quantization
- Committee Machines
- Mixture Models

### Programmes containing this module

- MEng Computer Science/Software Engineering [4754]
- MEng Computer Science/Software Engineering with an Industrial Year [9501]
- MRes Natural Computation [9048]
- MSci Mathematics and Computer Science [5197]
- MSci Mathematics and Computer Science with an Industrial Year [9496]
- MSci Pure Mathematics and Computer Science [5256]
- MSci Pure Mathematics and Computer Science with an Industrial Year [9498]