Neural Networks (G5015)

15 credits, Level 6

Spring teaching

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.

Teaching

67%: Lecture
33%: Practical (Laboratory)

Assessment

100%: Coursework (Problem set)

Contact hours and workload

This module is approximately 150 hours of work. This breaks down into about 44 hours of contact time and about 106 hours of independent study. The University may make minor variations to the contact hours for operational reasons, including timetabling requirements.

We regularly review our modules to incorporate student feedback, staff expertise, as well as the latest research and teaching methodology. We鈥檙e planning to run these modules in the academic year 2024/25. However, there may be changes to these modules in response to feedback, staff availability, student demand or updates to our curriculum.

We鈥檒l make sure to let you know of any material changes to modules at the earliest opportunity.