Description
Aims:
This module covers supervised approaches to machine learning (ML). Our goal will be to gain intuition about a number of ML methodologies, how they function, where they perform well, poorly and so forth. These intuitions will be given as mathematical results which will be supported by proof.
Intended learning outcomes:
On successful completion of the module, a student will be able to:
- Gain in-depth familiarity with various classical and contemporary supervised learning algorithms.
- Understand the underlying limitations and principles that govern learning algorithms and ways of assessing and improving their performance.
Indicative content:
The module consists of both foundational topics for supervised learning such as Linear Regression, Nearest Neighbours and Kernelisation as well contemporary research areas such as multi-task learning and optimisation via proximal methods.
The following are indicative of the topics the module will typically cover:
- Nearest Neighbours.
- Linear Regression.
- Kernels and Regularisation
- Support Vector Machines.
- Gaussian Processes.
- Decision Trees.
- Ensemble Learning.
- Sparsity Methods.
- Multi-task Learning.
- Proximal Methods.
- Semi-supervised Learning.
- Neural Networks.
- Matrix Factorization.
- Online Learning.
- Statistical Learning Theory.
Requisites:
To be eligible to select this module as an optional or elective, a student must: (1) be registered on a programme and year of study for which it is formally available; and (2) have high competency with Multivariable Calculus, Probability and Combinatorics, and Linear Algebra such that they can reprove basic results as well as novel results.
The module is mathematical in nature. As such there is a significant proportion devoted to formal theorems and proofs.
Module deliveries for 2024/25 academic year
Last updated
This module description was last updated on 19th August 2024.
Ìý