Computing
Neural Networks
Module code: G5015
Level 6
15 credits in spring semester
Teaching method: Lecture, Laboratory
Assessment modes: Coursework
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.
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.