Unit information: Machine Learning Paradigms in 2019/20

Unit name	Machine Learning Paradigms
Unit code	COMSM0025
Credit points	10
Level of study	M/7
Teaching block(s)	Teaching Block 1 (weeks 1 - 12)
Unit director	Professor. Peter Flach
Open unit status	Not open
Pre-requisites	None
Co-requisites	None
School/department	School of Computer Science
Faculty	Faculty of Engineering

Description including Unit Aims

This unit gives an in-depth overview of Machine Learning, exploring both unity and diversity among different ML paradigms and why this diversity is needed and how it can be exploited. The paradigms covered include: Introduction: tasks, models and features; Tree and Rule models; Linear and Distance-based models; Probabilistic models; Model ensembles; Deep learning. The unit will provide students with a solid analytical and practical framework for further work in data-driven AI.

Intended Learning Outcomes

After successfully completing this unit, you will be able to

1. Choose an appropriate learning algorithm for a given problem;
2. Use machine learning algorithms in solving classification problems;
3. Understand theoretical and practical limitations of machine learning.

Teaching Information

20 lectures; problem classes; unsupervised lab sessions.

Assessment Information

Coursework involving a significant comparative study of performance of different learning algorithms on a provided real-world data-set. This will be assessed through a written report (2,000 words + appendices). (50%) ILO 1-3

Viva/Oral Examination (50%) ILO 1-3

Reading and References

Machine Learning: The Art and Science of Algorithms that Make Sense of Data. Peter Flach. Cambridge University Press. September 2012.