COMP47490 Machine Learning (UG)

Academic Year 2022/2023

Note that from 2021/22, this module is primarily meant for UG students.
The objective of this module is to familiarise students with the fundamental theoretical concepts in machine learning, as well as to instruct students in the practical aspects of applying machine learning algorithms. Key techniques in supervised machine learning will be covered, such as classification using decision trees and nearest neighbour algorithms, and regression analysis. A particular emphasis will be placed on the evaluation of the performance of these algorithms. In unsupervised machine learning, a number of popular clustering algorithms will be presented in detail. Further topics and applications of machine learning will also be introduced. COMP47490 requires strong mathematical ability, as some of the algorithms require some understanding of linear algebra and statistical concepts.

Show/hide contentOpenClose All

Curricular information is subject to change

Learning Outcomes:

On completion of this module, students will be able to: 1) Distinguish between the different categories of machine learning algorithms; 2) Identify a suitable machine learning algorithm for a given application or task; 3) Run and evaluate the performance of a range of algorithms using various evaluation metrics; 4) be able to use Python and scikit-learn for machine learning tasks using real datasets.

Indicative Module Content:

Classification Techniques including kNN, Decision Trees, Naive Bayes and SVM
Regression
Gradient Descent and Neural Networks
Ensembles
Evaluation Methodology and Measures
Introduction to Reinforcement Learning
Unsupervised learning techniques including dimensionality reduction, partitional and hierarchical clustering
Running machine learning tasks using Python/Scikit-learn

Student Effort Hours: 
Student Effort Type Hours
Lectures

12
Tutorial

24
Autonomous Student Learning

100
Total

136
Approaches to Teaching and Learning:
Practical Labs; Continuous Assessment; enquiry & problem-based learning; 
Requirements, Exclusions and Recommendations
Learning Recommendations:

This module requires strong mathematical ability, as some of the algorithms require some understanding of linear algebra and statistical concepts.


Module Requisites and Incompatibles
Pre-requisite:
COMP30030 - Introduction to AI

Incompatibles:
COMP30120 - Intro to Machine Learning, COMP47460 - Machine Learning (Blended Del), COMP47750 - Machine Learning with Python


 
Assessment Strategy  
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Assignment: Assignment 1: Applying ML techniques in some simplified real-world application Unspecified n/a Graded No

20
Multiple Choice Questionnaire: A number of Brightspace quizzes to test the understanding of theoretical and application concepts. In addition, this includes submission of tutorial exercises and participation in the tutorials. Throughout the Trimester n/a Graded No

20
Assignment: Assignment 2: Applying ML techniques in some simplified real-world application Unspecified n/a Graded No

20
Examination: A final exam to test the theoretical understanding of machine learning concepts 2 hour End of Trimester Exam No Alternative linear conversion grade scale 40% No

40

Carry forward of passed components
No
 
Resit In Terminal Exam
Spring No
Please see Student Jargon Buster for more information about remediation types and timing. 
Feedback Strategy/Strategies

• Feedback individually to students, post-assessment

How will my Feedback be Delivered?

Not yet recorded.

"Machine Learning" by Tom Mitchell
"Fundamentals of Machine Learning for Predictive Data Analytics" by John D. Kelleher, Brian Mac Namee, Aoife D'Arcy
"Machine Learning: The Art and Science of Algorithms that Make Sense of Data" by Peter Flach
"The Elements of Statistical Learning: Data Mining, Inference and Prediction" by Trevor Hastie, Robert Tibshirani and Jerome Friedman
Name Role
Dr Deepak Ajwani Lecturer / Co-Lecturer
Mr Ryan O'Connor Tutor