Machine Learning and Applications

COMP 4910SED

Course Guide

COMP 4910SED

Course Guide

Machine Learning and Applications

Course Start Date

N/A

Course Level

N/A

Length in Terms

N/A

Credits

N/A

Language

N/A

Fees ($) (including lab fees)

N/A

Future Terms

Quota and Schedule

Course Start Date	Course Level	Length in Terms	Credits	Language	Fees ($) (including lab fees)	Future Terms
N/A	N/A	N/A	N/A	N/A	N/A

Quota and Schedule

Course Coordinator:

Dr Tabitha TAO Bishenghui, BEng, MSc (PolyU); PhD (MUST)

Course Developer:

Kendrew LAU Chu-man, Consultant

COMP 4910SED Machine Learning and Applications is a two-term, six-credit-unit, 4000-level course within the Bachelor of Computing with Honours in Internet Technology (BCITH) programme suite and the Bachelor of Science with Honours in Computing and Networking (BSCICNH) programme suite. It is an elective course for BCITH and BSCICNH. The course assumes students have fundamental knowledge of computer programming, data structures and algorithm design. The course is designed to provide students with a foundation in machine learning, and then help them establish their knowledge of different areas of machine learning applications.

Aims

The course aims to:

provide students with fundamental concepts and basic algorithms of machine learning and data mining; and
enable students to apply machine learning and data mining in creating software to solve real-world problems.

Contents

The course consists of the following study units:

Introduction to machine learning
Essential Python programming and tools
How machine learning and data mining work
Supervised learning: Principles and basic algorithms
Supervised learning: Advanced algorithms
Unsupervised learning: Clustering
Unsupervised learning: Association analysis and recommender systems
Reinforcement learning

Learning support

Five forms of tutor/student interaction will be provided in this course, including tutorials, surgeries, an online discussion board, e-mail and telephone tutoring.

Tutors will conduct ten two-hour in-person tutorial and six two-hour surgery sessions. At these sessions, tutors will review and reinforce key concepts, discuss topical issues, answer student questions, and provide assistance related to assignments.

Assessment

There will be three assignments (50%) and a final examination (50%). Students are required to submit assignments through the Online Learning Environment (OLE).

Online requirement

This course is supported by the Online Learning Environment (OLE). The most updated course material, course news and announcements are disseminated through the OLE. The use of the OLE is mandatory for this course.

Equipment

Students need access to a personal computer with Internet access. The minimum requirements are:

Microsoft Windows 10 or above
A quad-core processor
8 GB memory
50 GB free hard disk space

Software

You will need access to the following software:

An operating system of Microsoft Windows Vista or above
Web browser: Internet Explorer 8 or compatible

Reference book(s)

Russell, S. & Norvig, P. (2021). Artificial intelligence: A modern approach (4th ed.). Prentice Hall.
Lucci, S. & Kopec, D. (2020). Artificial intelligence in the 21st century (3rd ed.). Mercury Learning & Information.

Students with disabilities or special educational needs

The audio and visual components of this course may cause difficulties for students with hearing or vision impairments. You are encouraged to seek advice from the Course Coordinator before enrolling in this course.