COM5203 - Machine Learning

Objectives:

Assessment tasks are designed to enable students to demonstrate the Learning and Employability outcomes for the relevant level of study. Level Learning Outcomes are embedded in the assessment task(s) at that level. This enables a more integrated view of overall student performance at each level.

Content:

This module furnishes students with a foundational comprehension of essential machine learning principles. It serves as a gateway, acquainting students with diverse machine learning problems and the rudimentary algorithms employed to tackle them. Encompassing pivotal concepts, the module lays the groundwork for more advanced and specialised courses by delving into the fundamental knowledge of machine learning. On completion of this module, students are equipped with the proficiency to navigate intricate machine learning landscapes. The comprehensive exploration not only cultivates theoretical understanding but also nurtures the practical skills necessary for addressing complex challenges in the ever-evolving field of machine learning. This foundational knowledge forms the cornerstone for students venturing into more intricate and specialised aspects of machine learning in subsequent areas of study.

Learning and Teaching Information:

Workshops
Hours: 60
Intended Group Size: Cohort

Guided independent study
Hours: 240

Further Details Relating to Assessment

Assessment tasks are designed to measure the extent to which you have satisfied the Level Learning Outcomes for your programme. Some modules, for example where there are professional body (PSRB) requirements, will also test for module-specific skills and knowledge.

Machine Learning Challenge Workbook 1: This assessment is a workbook with various challenges for which students need to provide solutions. For example, they may need to implement linear regression.

Machine Learning Challenge Workbook 2: This assessment is a workbook with various challenges for which students need to provide solutions. For example, they may need to implement random forest.

In computer science classes, formative assessment serves to bolster the skills essential for module success. This may include engaging in practical labs, undertaking design and modelling tasks, delivering case study presentations, completing short quizzes and conducting specific investigation tasks. The provision of formative feedback is integrated seamlessly into class sessions, ensuring an ongoing and iterative process to enhance learning outcomes.

Full details are available in the Module Handbook.

Assessment:

001 Machine Learning Challenge Workbook 1; 1500 word equiv; Mid sem 1 50%
002 Machine Learning Challenge Workbook 2; 1500 word equiv; End sem 1 50%

Fact File

Module Coordinator - PRS_CODE=
Level - 5
Credit Value - 30
Pre-Requisites - NONE
Semester(s) Offered - 5S1

Click here to go back to previous page