Module overview
Machine Learning is about extracting useful information from large and complex datasets. The subject is a rich mixture of concepts from function analysis, statistical modelling and computational techniques. The module will introduce the fundamental principles of the subject, where you will learn the theoretical basis of how learning algorithms are derived and when they are optimally applied, and gain hands-on experience in laboratory-based sessions.
Aims and Objectives
Learning Outcomes
Subject Specific Practical Skills
Having successfully completed this module you will be able to:
- Systematically work with data to learn new patterns or concepts
- Gain facility in designing experiments and measuring performance with appropriate metrics
Knowledge and Understanding
Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:
- Demonstrate knowledge of simple supervised learning methods
- Understand the relationship between machine learning and biological learning
- Demonstrate knowledge of simple unsupervised learning methods
Subject Specific Intellectual and Research Skills
Having successfully completed this module you will be able to:
- Characterise data in terms of explanatory models
- Explore the real-world impact of training complex AI models
- Use data to reinforce one/few among many competing explanatory hypotheses
- Be able to derive simple learning algorithms for regression and classification
Syllabus
Historical Perspective
- Biological motivations (e.g. the McCulloch and Pitts neuron, Rosenblatt's perceptron, Hebbian learning).
- Statistical motivations (Bayes rule, etc.)
Theory
- Generalisation: What is learning from data?
- The power of machine learning methods: What is a learning algorithm? What can they do?
- Experiment design & measuring performance
Supervised Learning
- Classification using Bayesian principles
- Fisher's Linear Discriminant
- Linear regression & simple regularisation
- Learning linear decision boundaries
- Introduction to neural networks & multi-layer perceptrons (MLPs)
- Features and discriminant analysis
Optimisation
- Basics of gradient-based optimisation (simple Gradient Descent and SGD)
Data handling and unsupervised learning
- Principal Components Analysis (PCA)
- K-Means clustering
- Hierarchical clustering
Learning and Teaching
Teaching and learning methods
The module consists of:
- Lectures
- Combined tutorials and computing laboratory sessions
Type | Hours |
---|---|
Revision | 10 |
Guided independent study | 80 |
Preparation for scheduled sessions | 10 |
Specialist Laboratory | 16 |
Lecture | 24 |
Total study time | 140 |
Assessment
Summative
This is how we’ll formally assess what you have learned in this module.
Method | Percentage contribution |
---|---|
Exam | 50% |
Class Test | 10% |
Computing assignment | 20% |
Computing assignment | 20% |
Referral
This is how we’ll assess you if you don’t meet the criteria to pass this module.
Method | Percentage contribution |
---|---|
Exam | 100% |
Repeat
An internal repeat is where you take all of your modules again, including any you passed. An external repeat is where you only re-take the modules you failed.
Method | Percentage contribution |
---|---|
Exam | 100% |