Machine Learning module (CS31006)
Study supervised machine learning and gain practical experience in training and evaluating machine learning models
10
CS31006
Machine learning (ML) is a rapidly growing field that has the potential to revolutionise industries such as healthcare, finance, and transportation.
With a solid foundation in machine learning, you can analyse vast amounts of data, make predictions, or create intelligent agents. This enables you to implement innovative solutions to solve real-world problems.
Whether your passion is data science or software development, the ML skillset is highly sought after in both industries. A strong understanding of machine learning will help you future-proof your career and approach complex problem-solving settings.
What you will learn
In this module, you will:
- study supervised machine learning and its applications
- learn about classification and regression problems
- learn about important principles such as generalisation, data splits, and cross-validation
- explore common machine learning algorithms, such as K-nearest neighbour, and linear regression
- discuss parameter optimisation and commonly used optimisation algorithms
- study how neural networks work and the algorithms used to train them
- discuss deep learning and regularisation
By the end of this module, you will be able to:
- explain key theoretical concepts from machine learning such as generalisation and regularisation
- discuss well-known supervised learning algorithms
- train and evaluate machine learning methods using an industry standard software framework
- describe how to estimate predictive performance of supervised learning methods on a given dataset
- design and conduct machine learning experiments
Assignments / assessment
- supervised machine learning evaluation (50%)
- written exam (50%)
Teaching methods / timetable
You will learn by taking a hands-on approach. This will involve taking part in tutorials and practical sessions.
Learning material is provided through videos, review notes, examples, and tutorial questions.
This is a half-semester module. You will study another 10 credit module during the other half of this semester.
Courses
This module is available on following courses: