COMP6246 Machine Learning Technologies (MSc)
Module Overview
Machine Learning is about extracting useful information from large and complex datasets. The module will cover the practical basis of how learning algorithms are can be applied. You will gain hands-on experience in laboratory-bases sessions. Exclusions: Cannot be taken with COMP3206 or COMP3222 or COMP3223 or COMP6229 or COMP6245.
Aims and Objectives
Module Aims
To give students a solid grounding in the concepts of machine learning using hands-on practical work and algorithmic-level understanding.
Learning Outcomes
Knowledge and Understanding
Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:
- The algorithmic basis of machine learning algorithms
- Implementation issues in learning algorithms and the evaluation of their performance.
Subject Specific Intellectual and Research Skills
Having successfully completed this module you will be able to:
- Characterise data in terms of explanatory models
- Critically appraise the uses of Deep Learning
- Appreciation of the landscape of tools used for modern machine learning
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 expertise in working with machine learning to make predictions in a scientific computing environment
Syllabus
Historical Perspective - Biological motivations: the McCulloch and Pitts neuron, Hebbian learning. - Conceptual motivations Tools in machine learning - Libraries - Implementing and evaluating algorithms Supervised Learning - Perceptron Algorithm - Support Vector Classification and Regression - Neural networks/multi-layer perceptrons (MLP) Data handling and unsupervised learning - Principal Components Analysis (PCA) - K-Means clustering Regression and Model-fitting Techniques - Linear regression Deep Learning - Deep Neural Networks (CNN, RNN) Case Studies - Example applications: Speech, Vision, Natural Language, Bioinformatics.
Learning and Teaching
Teaching and learning methods
Lectures, labs and guided self-study
Type | Hours |
---|---|
Revision | 10 |
Specialist Laboratory | 20 |
Completion of assessment task | 75 |
Lecture | 24 |
Wider reading or practice | 21 |
Total study time | 150 |
Resources & Reading list
Aurélien Géron. Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems.
Assessment
Summative
Method | Percentage contribution |
---|---|
Coursework | 50% |
Examination (2 hours) | 50% |
Repeat
Method | Percentage contribution |
---|---|
Examination | 100% |
Referral
Method | Percentage contribution |
---|---|
Examination (2 hours) | 100% |
Repeat Information
Repeat type: Internal & External