Neural Networks (G5015)

15 credits, Level 6

Spring teaching

Neural networks (NNs) power many of today’s most advanced artificial intelligence and machine learning tools.

On this module, you’ll cover the basic principles behind different types of NNs. You’ll explore how to improve their performance, how they’re used, and study:

  • loss functions for regression and classification
  • support vector machines
  • NNs as universal function approximators
  • multi-layer perceptrons
  • convolutional neural networks (CNNs)
  • recurrent NNs, including long-short-term-memory (LSTM)
  • advanced architectures and attention mechanisms
  • key ideas such as 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, Test)

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 2025/26. 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.

Courses

This module is offered on the following courses: