Aims and Fit of Module

The module aims to provide students with a comprehensive understanding of machine learning algorithms, techniques, and applications at an advanced level, and equip students with the ability to apply machine learning techniques to real-world problems.

Learning outcomes

A	Demonstrate a comprehensive and deep understanding of the fundamental concepts, theories, and algorithms in machine learning.
B	Expertly implement different classic and advanced machine learning algorithms.
C	Systematically evaluate the performance of machine learning models using appropriate metrics and techniques. 
D	Analyse machine learning experimental results, interpret findings, and critically appraise outcomes and conclusions
E	Use appropriate techniques to devise the best implementation of machine learning algorithms to solve practical learning problems.

Method of teaching and learning

The teaching philosophy of the module adopts the philosophy of Syntegrative Education. This has meant that the teaching delivery pattern, which follows more intensive block teaching, allows more meaningful contribution from industry partners. This philosophy is carried through also in terms of assessment, with reduction on the use of exams and increase in coursework, especially problem-based assessments that are project focused. The delivery pattern provides space in the semester for students to concentrate on completing the assessments.

This module will be delivered through lectures, seminars and labs. Lectures are delivered to present key theoretical concepts, algorithms, and methodologies in machine learning. Lab provides students with hands-on experience and practical application of machine learning techniques. Lab sessions are designed to reinforce the theoretical concepts covered in lectures and allow students to gain proficiency in implementing machine learning algorithms and models. Private study will provide time for reflection and consideration of lecture material and background reading. Seminar is designed to cater a common ground for students to interact with lecturers about the practical application of machine learning techniques. It is a platform in which students can be exposed to the specific industrial needs for machine learning technology and gain better understanding about the materials they have learnt from lectures and practical. Students will be assessed based on the skills and knowledge they learnt from the classroom. The assessment will be conducted in the form of individual project. A rubric will be formulated to evaluate the performance of each student.

In addition, students will be expected to devote unsupervised time to private study. Private study will provide time for reflection and consideration of lecture material and background reading.