Module 06-32167 (2022)
Neural Computation
Level 3/H
Jinming Duan Konstantinos Kamnitsas Yunwen Lei | Semester 1 | 20 credits |
Co-ordinator: Konstantinos Kamnitsas
Reviewer: Jinming Duan
The Module Description is a strict subset of this Syllabus Page.
Outline
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.
Aims
The aims of this module are to:
- 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
Learning Outcomes
On successful completion of this module, the student should be able to:
- 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
Restrictions
Students must have A-Level Mathematics or equivalent
Taught with
- 06-32212 - Neural Computation (Extended)
Cannot be taken with
- 06-32212 - Neural Computation (Extended)
Assessment
- Main Assessments: Examination (80%) and continuous assessment via coursework (20%)
- Supplementary Assessments: Examination (100%)
Detailed Syllabus
- Introduction to Neural Networks and their History
- Linear Regression and Learning with Gradient Descent
- Single Layer Perceptrons
- Learning and Generalization in Single Layer Perceptrons
- The Generalized Delta Rule, Practical Considerations
- Learning in Multi-Layer Perceptrons - Back-Propagation
- Modern Optimization Algorithms
- Under-Fitting and Over-Fitting
- Convolutional Neural Networks
- Recurrent Neural Networks
- Auto-encoders
- Variational Auto-encoders
- Generative Adversarial Neural Networks
Programmes containing this module
- BSc Artificial Intelligence & Computer Science [0144]
- BSc Artificial Intelligence & Computer Science with an Industrial Year [9502]
- BSc Artificial Intelligence & Computer Science with Study Abroad [452B]
- BSc Computer Science [4436]
- BSc Computer Science with an Industrial Year [9499]
- BSc Computer Science with Digital Technology Partnership (PwC) [610C]
- BSc Computer Science with Digital Technology Partnership (Vodafone) [893C]
- BSc Computer Science with Study Abroad [5571]
- BSc Mathematics and Computer Science [5196]
- BSc Mathematics and Computer Science with an Industrial Year [9495]
- MEng Computer Science/Software Engineering [4754]
- MEng Computer Science/Software Engineering with an Industrial Year [9501]
- MSci Computer Science [4443]
- MSci Computer Science with an Industrial Year [9509]
- MSci Computer Science with Study Abroad [5576]
- MSci Mathematics and Computer Science [5197]
- MSci Mathematics and Computer Science with an Industrial Year [9496]