Module 06-32212 (2022)

This course focuses on artificial neural networks and their use in machine learning. It covers the fundamental underlying theory, as well as methodologies for constructing modern deep neural networks, which nowadays have practical applications in a variety of industrial and research domains. The course also provides practical experience of designing and implementing a neural network for a real-world application.

• Introduce some of the fundamental techniques and principles of neural networks
• Investigate some common neural-network architectures and their applications
• Present neural networks in the larger context of state-of-the-art techniques of automated learning

• Describe and explain some of the principal architectures and learning algorithms of neural computation
• Explain the learning and generalisation aspects of neural computation networks
• Demonstrate an understanding of the benefits and limitations of neural networks in comparison to other machine learning methods.
• Develop and apply neural network models to specific technical and scientific problems

Students must have A-Level Mathematics or equivalent

• Main Assessments: Examination (80%) and continuous assessment via coursework (20%)
• Supplementary Assessments: Examination (100%)

1. Introduction to Neural Networks and their History
2. Linear Regression and Learning with Gradient Descent
3. Single Layer Perceptrons
4. Learning and Generalization in Single Layer Perceptrons
5. The Generalized Delta Rule, Practical Considerations
6. Learning in Multi-Layer Perceptrons - Back-Propagation
7. Modern Optimization Algorithms
8. Under-Fitting and Over-Fitting
9. Convolutional Neural Networks
10. Recurrent Neural Networks
11. Auto-encoders
12. Variational Auto-encoders
13. Generative Adversarial Neural Networks