Neural Networks (G5015)
Note to prospective students: this content is drawn from our database of current courses and modules. The detail does vary from year to year as our courses are constantly under review and continuously improving, but this information should give you a real flavour of what it is like to study at СÀ¶ÊÓƵ.
We’re currently reviewing teaching and assessment of our modules in light of the COVID-19 situation. We’ll publish the latest information as soon as possible.
Neural Networks
Module G5015
Module details for 2024/25.
15 credits
FHEQ Level 6
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 Outline
Neural networks (NNs) are behind many of the most sophisticated and powerful artificial intelligence and machine learning tools used today. This module covers fundamental principles of NNs, different types of NN, methods to improve their performance, and their applications. Specific topics we’ll cover include:
• Loss functions for regression and classification
• Support vector machines
• NNs as universal function approximators
• Multi-layer perceptrons
• Convolutional NNs (CNNs)
• Recurrent NNs, including long-short-term-memory (LSTM)
• Advanced architectures and attention mechanisms
• Gradient descent, back-propagation, optimisers
• Regularisation, generalisation, gradient flow
• Encoding and feature learning
• Generative adversarial networks
• Deep reinforcement learning
• Graph neural networks
Library
1. Haykin S (1999). Neural networks. Prentice Hall International.
2. Bishop C (1995). Neural networks for pattern recognition. Oxford: Clarendon Press.
3. Duda RO, Hart PE and Stork DG (2001). Pattern Classification, John Wiley.
4. Ripley BD (1996). Pattern Recognition and Neural Networks. Cambridge University Press.
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.
| Type | Timing | Weighting |
|---|---|---|
| Coursework | 100.00% | |
| Coursework components. Weighted as shown below. | ||
| Problem Set | A2 Week 1 | 100.00% |
Timing
Submission deadlines may vary for different types of assignment/groups of students.
Weighting
Coursework components (if listed) total 100% of the overall coursework weighting value.
| Term | Method | Duration | Week pattern |
|---|---|---|---|
| Spring Semester | Lecture | 2 hours | 11111111111 |
| Spring Semester | Laboratory | 1 hour | 11111111111 |
How to read the week pattern
The numbers indicate the weeks of the term and how many events take place each week.
Dr James Bennett
Assess convenor
/profiles/415831
Please note that the University will use all reasonable endeavours to deliver courses and modules in accordance with the descriptions set out here. However, the University keeps its courses and modules under review with the aim of enhancing quality. Some changes may therefore be made to the form or content of courses or modules shown as part of the normal process of curriculum management.
The University reserves the right to make changes to the contents or methods of delivery of, or to discontinue, merge or combine modules, if such action is reasonably considered necessary by the University. If there are not sufficient student numbers to make a module viable, the University reserves the right to cancel such a module. If the University withdraws or discontinues a module, it will use its reasonable endeavours to provide a suitable alternative module.