COM7003 - Machine Learning

Objectives:

On successful completion of the module, students will be able to:
Demonstrate an understanding of a range of machine learning algorithms and predictive problem-solving techniques
Demonstrate detailed knowledge of the use of machine learning systems for data processing and analytics
Evaluate and optimise the performances of various machine learning methods for data analytics
Critically apply machine learning tools and techniques to improve decision-making and business insights.

Content:

The aim of this module is to equip students with the ability to tackle real-world problems in the field of data science and AI. With a focus on practical, problem-solving perspectives, they will learn the machine learning stages to model intelligent predictive solutions to help enterprises achieve sustainability in their businesses.

There will be an opportunity to practise a range of algorithms, from fundamental linear regression and decision trees to advanced techniques such as neural networks. Students will learn how to turn raw data into actionable insights, predict outcomes and uncover hidden secrets using industry-level tools. Students will also learn some fundamental ideas of deep learning.

Learning and Teaching Information:

Workshops may take different approaches relevant to the content. Students may be initially presented with the fundamental key concepts of machine learning to enable them to understand and analyse the material. These will be interactive in nature. If possible, there will be some guest visits undertaken by academics and industry practitioners. This may then be followed up by an opportunity for students to apply techniques to given scenarios, including additional examples covering further aspects of artificial intelligence and machine learning. The practical sessions are to provide students with experience of algorithm development and software implementations.

Workshops
Hours: 40
Intended Group Size: 50

Guided independent study
Hours: 260

Further details relating to assessment
Software Artefact: This software artefact produces a machine learning solution that is developed, tested and evaluated using a given real-world dataset. Students will be presented with a new or existing real-world dataset to implement a solution to a problem. They are required to formalise a problem in which they are interested to solve around the given dataset. Their solution must demonstrate detailed knowledge of the use of machine learning systems for data processing and analytics, evaluate and optimise the performances of various machine learning methods and critically apply machine learning tools and techniques to improve decision-making and business insights.

Students are required to provide the following:
- coding scripts, dataset/s, test cases, features, etc
- visualisation of results and
- project documentation, workability and interpretation of results.

Presentation: Students will be required to prepare an individual presentation to demonstrate the software artefact and show an understanding of the proposed machine learning solution.

In this module, formative assessment will be used to support the skills that contribute to the assessment. Formative assessment may include group discussions, visualisation and modelling tasks, case study presentations, short quizzes or specific research tasks. Formative feedback will be an ongoing process within class sessions.

Students should refer to the Module Handbook for further details on the module learning, teaching and assessment strategies.

Assessment:

001 Software artefact; 3,000 words; end of term 1 70%
002 Presentation (individual) 10 minutes; end of term 1 30%

Fact File

Module Coordinator - PRS_CODE=
Level - 7
Credit Value - 30
Pre-Requisites - NONE
Semester(s) Offered - 7T1

Click here to go back to previous page