Computing
Neural Networks
Module code: G5015
Level 6
15 credits in spring semester
Teaching method: Lecture, Laboratory
Assessment modes: Coursework
In recent years, neural computing has emerged as a practical technology, with successful applications in many fields. The majority of these applications are concerned with problems in pattern recognition. It has become widely acknowledged that successful applications of neural networks require a more principled approach.
On this module, you will experience a more focused treatment of neural networks than previously available, which reflects these developments.
By concentrating on the pattern recognition aspects of neural networks, you will explore important topics like:
- data pre-processing
- probability density estimation
- PCA/ICA and other information measures
- multi-layer perceptron
- radial basis function network
- support vector machines
- competitive learning
- mixture of experts and committee machines
- reinforcement learning.
You'll also learn how to apply neural networks to solving real world problems.
Pre-requisite
The course assumes an ability to write software in one appropriate programming language (e.g. Java, C, Python, Matlab). Basic knowledge of formal computational skills is also assumed.
Module learning outcomes
- refer to relevant mathematical concepts to describe how modern, deep neural networks can be used as universal function approximators.
- describe and critique the principles and applications of different neural network architectures.
- describe and critique the principles underlying different design considerations and techniques used to optimise the performance of neural networks.
- apply their knowledge of neural networks by building, optimising, and analysing a neural network for a real-world problem.