Gwybodaeth Modiwlau

Module Identifier

CS36220

Module Title

Machine Learning

Academic Year

2022/2023

Co-ordinator

Dr Neil Mac Parthalain

Semester

Semester 1

Exclusive (Any Acad Year)

CS36110

Course Delivery

Assessment

Assessment Type	Assessment length / details	Proportion
Semester Assessment	Practical Assignment (3,000 words)	50%
Semester Exam	2 Hours	50%
Supplementary Assessment	Practical Assignment (3,000 words)	50%
Supplementary Exam	2 Hours	50%

Learning Outcomes

On successful completion of this module students should be able to:

Demonstrate a knowledge and understanding of the Machine Learning paradigm and the main approaches to machine learning.

Describe important, different machine learning techniques and algorithms and how they perform.

Select an appropriate Machine Learning technique and describe how this can be applied as a suitable solution for a given application problem or domain.

Compare and contrast the properties and limitations of different Machine Learning techniques and algorithms and discuss the implementational challenges involved in applying them.

Demonstrate a practical understanding of the use of Machine Learning techniques and algorithms by applying them to various domain problems.

Brief description

The module provides an introduction to machine learning and a number of different machine learning techniques and algorithms. It places significant emphasis on the practical elements and utilises practical sessions in order to implement the knowledge acquired through the delivered lecture material.

Content

1. Introduction
Introduction to machine learning including example applications and classes of machine learning techniques

2. Decision Trees
Introduction to decision trees (classification trees and regression trees); over-fitting; pruning; application example

3. Bayesian Learning
Bayes' theorem/rule; maximum likelihood; maximum a posteriori; naive Bayes classifier; application example

4. Artificial Neural Networks (approx. 4 lectures)
Introduction to perceptrons, and perceptron-based artificial neural networks; linear separability; activation functions; back-propagation; application example

5. Support Vector Machines
maximum margin hyperplane; kernel trick; kernel functions; soft margins; application example

6.Selected Additional ML Topics
Introduction and discussion of another important machine learning technique topic, e.g., reinforcement learning, handling uncertainty, genetic programming

7. Summary and Revision

Module Skills

Skills Type	Skills details
Application of Number
Communication	Via written examination and report writing.
Improving own Learning and Performance	Presents a general approach to machine learning. The principles can be adapted to any particular situation and are not specific to any domain.
Information Technology	Use of computing to solve real-world problems
Personal Development and Career planning	Real-world problems will be presented as part of the taught material and the assignments.
Problem solving	Via in-lecture problem-solving exercises
Research skills	Via in-lecture problem-solving exercises
Subject Specific Skills	Demonstrate a knowledge and understanding of the Machine Learning paradigm and the main approaches to machine learning.
Team work	Group work is not part of this module

Notes

This module is at CQFW Level 6