Description
Aims:
The module aims to empower the students with the mathematical framework, tools, and reasoning to analyse and understand how machine learning algorithms are operating and behaving. This aims at developing generations of practitioners of machine learning algorithms who are aware of the foundational concepts and are comfortable with the implications and limitations of the deployment of such algorithms, notably in sustainable development or healthcare applications.
Intended learning outcomes:
On successful completion of the module, a student will be able to:Ìý
- Demonstrate understanding the foundations of artificial intelligence, relating in particular to statistical learning theory and theoretical machine learning.Ìý
- Evaluate the settings under which machine learning algorithms enjoy certain desirable properties, such as sparsity, reduced environmental footprints, privacy-preserving capabilities, to name but a few.Ìý
- Describe the foundations of artificial intelligence and how those foundations are crucial to understand and deploy intelligent systems in the real world.
Indicative content:
The following is indicative of the topics the module will typically cover:
This module covers the fundamentals of artificial intelligence and offers an introduction to the mathematics underpinning machine learning. The module starts with an introduction to artificial intelligence, machine learning, data, and statistical learning theory, including the notions of risk, generalisation bounds, model complexity, bias-variance trade-off, overfitting, regularisation, evaluation and many others. Subsequently, we will present how these foundational ideas relate to different machine learning models that tackle problems using supervised, unsupervised and reinforcement learning. Classical results will be proven and discussed. The module will introduce some key algorithms which will be covered in greater depth in other modules. Furthermore, there are opportunities during the course to programmatically implement these models using real-world datasets. The module aims at providing an overview rather than diving into details. Ìý
Requisites:
To be eligible to select this module as an optional or elective, a student must be registered on a programme and year of study for which it is formally available.
Module deliveries for 2024/25 academic year
Last updated
This module description was last updated on 19th August 2024.
Ìý