Module description
The course consists of 10 weeks of lectures and practical tutorials. We will start with Python tutorial, followed by introduction to machine learning and Scikit-learn library. Then we will cover various classical machine learning topics, including regression, classification, dimensionality reduction, clustering and ensemble learning. In last two weeks we will have introduction to deep learning and Pytorch library.
To follow the course, you will need to install anaconda on your personal laptop. On the lab machines, this can be done through the software centre, and you will be guided through this process in Week 1. For week 9 and 10 you will need to use google colab, but you can also use it throughout the course. Installation instructions can be found here.
On completion of the course the students should:
- Have acquired a basic understanding of the most fundamental concepts related to machine learning;
- Understand and apply a range of commonly used machine learning techniques;
- Have acquired practical computational skills that are needed to manipulate complex datasets;
- Be able to apply techniques learnt to domains related to biomedical applications.
Assessment details
| Written Exam |
50% |
| Coursework 1 |
25% |
| Coursework 2 |
25% |
Semester 1 only Study Abroad students will be set an alternative assessment to the January exam (100% Coursework)
Educational aims & objectives
The module will provide students with a grounding in fundamental machine learning topics as well as practical examples of how to apply these techniques to real world data. Topics will include the foundations of machine learning, linear classification and regression, Support Vector Machines, Penalised Regression, Dimensionality Reduction and Manifold Learning, as well as ensemble learning (Random Forests, Bagging and Boosting) and advanced image segmentation techniques.
Learning outcomes
On completion of the course the students should:
- have acquired a basic understanding of the most fundamental concepts related to machine learning.
- understand and apply a range of commonly used machine learning techniques.
- have acquired practical computational skills that are needed to manipulate complex datasets.
- be able to apply techniques learnt to domains related to biomedical applications.