Aims and Fit of Module

Machine learning is a set of techniques that allow machines to learn from data and experience, rather than requiring humans to specify the desired behaviour by hand. Over the past two decades, machine learning techniques have become increasingly central both in AI as an academic field, and in the technology industry. This course provides a broad introduction to some of the most commonly used ML algorithms. It also serves to introduce key algorithmic principles which will serve as a foundation for more advanced courses, such as deep learning.

Learning outcomes

A Explain the fundamental principles, assumptions, and limitations of major machine learning algorithms.
B Analyze the theoretical and empirical properties of machine learning algorithms, including model complexity, generalization, and sources of error.
C Apply selected machine learning algorithms to solve practical problems using appropriate training and evaluation procedures.
D Compare machine learning algorithms and tune key hyperparameters for specific problems, justifying the choices based on model assumptions, performance and generalization.

Method of teaching and learning

Students are required to attend two hours of lectures each week, focusing on theoretical concepts and foundational knowledge. Additionally, students will take part in 4 hours of supervised lab sessions every two weeks offering hands-on experience and real-world applications of the lecture topics.

Students are also encouraged to dedicate around eight hours per week to independent study. This time should be spent reflecting on lecture content, conducting extensive research, and reading broadly on the subject. 

Continuous assessment and a final integrated project will be used to evaluate students’ theoretical understanding as well as their ability to apply machine learning methods to practical problems.