Students

COMP8221 – Advanced Machine Learning

2026 – Session 1, In person-scheduled-weekday, North Ryde

General Information

Download as PDF
Unit convenor and teaching staff Unit convenor and teaching staff Convenor, Lecturer
Xuhui Fan
xuhui.fan@mq.edu.au
4RPD 319
Lecturer
Yanqiu Wu
yanqiu.wu@mq.edu.au
3IR level 3 office
Credit points Credit points
10
Prerequisites Prerequisites
COMP6420 or Admission to the GradDipRes or GradCertRes
Corequisites Corequisites
Co-badged status Co-badged status
Unit description Unit description

In contrast to other units focussing on foundations or applications of machine learning, this unit focusses on theoretical underpinnings of machine learning, and deep learning in particular, and the advanced techniques in machine learning that come from understanding them.  The unit covers the theoretical properties of various kinds of machine learning approaches, and advanced techniques like autoencoders, representation learning, Generative Adversarial Networks and deep generative models.

Learning in this unit enhances student understanding of global challenges identified by the United Nations Sustainable Development Goals (UNSDGs) Industry, Innovation and Infrastructure

Important Academic Dates

Information about important academic dates including deadlines for withdrawing from units are available at https://www.mq.edu.au/study/calendar-of-dates

Learning Outcomes

On successful completion of this unit, you will be able to:

  • ULO1: Explain the theoretical properties of a range of machine learning approaches.
  • ULO2: Explain various advanced techniques and architectures in machine learning, and what kinds of problems they can be used to solve.
  • ULO3: Design and implement a solution to a problem requiring one of the advanced machine learning techinques.

General Assessment Information

Assignment type

Assignment 1: This is an individual assignment. Each student must work by themselves and submit their individual assignment.

Assignment 2: This is a group assignment. All the students are required to form a 1~3 person group. 

Release Dates

Assignment 1: To be released no later than 22th March, 2026.

Assignment 2: To be released no later than 3th May, 2026.

Requirement to Pass this Unit 

To pass this unit, you must achieve a total mark equal to or greater than 50%.   

 Late Submission Policy

  • 5% penalty per day: If you submit your assessment late, 5% of the total possible marks will be deducted for each day (including weekends), up to 7 days.

    • Example 1 (out of 100): If you score 85/100 but submit 20 hours late, you will lose 5 marks and receive 80/100.

    • Example 2 (out of 30): If you score 27/30 but submit 1 day late, you will lose 1.5 marks and receive 25.5/30.

  • After 7 days: Submissions more than 7 days late will receive a mark of 0.

  • Extensions:

    • Automatic short extension: Some assessments are eligible for automatic short extension. You can only apply for an automatic short extension before the due date.

    • Special Consideration: If you need more time due to serious issues and for any assessments that are not eligible for Short Extension, you must apply for Special Consideration.

Need help? Review the Special Consideration page HERE

Assignments where Late Submissions will be accepted/not accepted: 

  • Assignment #1: Yes, Standard Late Penalty applies. 

  • Assignment #2: Yes, Standard Late Penalty applies. 

  • Final exam: No, unless Special Consideration is Granted

Special Consideration 

The Special Consideration Policy aims to support students who have been impacted by short-term circumstances or events that are serious, unavoidable and significantly disruptive, and which may affect their performance in assessment. If you experience circumstances or events that affect your ability to complete the assessments in this unit on time, please inform the convenor and submit a Special Consideration request through http://connect.mq.edu.au/.

Assessment Tasks

Name Weighting Hurdle Due Groupwork/Individual Short Extension AI assisted?
Assignment 1 30% No 03/05/2026 Individual No Open AI
Assignment 2 30% No 31/05/2026 Group No Open AI
Exam 40% No Exam period Individual No Observed

Assignment 1

Assessment Type 1: Experiential task
Indicative Time on Task 2: 30 hours
Due: 03/05/2026
Weighting: 30%
Groupwork/Individual: Individual
Short extension 3: No
AI assisted?: Open AI

This assignment focuses on the design, implementation, and evaluation of a deep generative model. Students will choose one modeling approach and apply it to a relevant dataset. The project involves building the model, analyzing its performance, and presenting findings through visualizations and a written report.
On successful completion you will be able to:
  • Explain the theoretical properties of a range of machine learning approaches.
  • Design and implement a solution to a problem requiring one of the advanced machine learning techinques.

Assignment 2

Assessment Type 1: Experiential task
Indicative Time on Task 2: 30 hours
Due: 31/05/2026
Weighting: 30%
Groupwork/Individual: Group
Short extension 3: No
AI assisted?: Open AI

In this assignment, students will undertake an applied or research-based project in either Graph Neural Networks (GNNs) or Deep Reinforcement Learning (DRL). The project involves identifying a suitable problem or study, developing or adapting methods to address it, and documenting results in a comprehensive report supported by code.
On successful completion you will be able to:
  • Explain the theoretical properties of a range of machine learning approaches.
  • Design and implement a solution to a problem requiring one of the advanced machine learning techinques.

Exam

Assessment Type 1: Examination
Indicative Time on Task 2: 20 hours
Due: Exam period
Weighting: 40%
Groupwork/Individual: Individual
Short extension 3: No
AI assisted?: Observed

Demonstrate an understanding of a selection of topics covered in the unit.
On successful completion you will be able to:
  • Explain the theoretical properties of a range of machine learning approaches.
  • Explain various advanced techniques and architectures in machine learning, and what kinds of problems they can be used to solve.
  • Design and implement a solution to a problem requiring one of the advanced machine learning techinques.

1 If you need help with your assignment, please contact:

  • the academic teaching staff in your unit for guidance in understanding or completing this type of assessment
  • the Writing Centre for academic skills support.

2 Indicative time-on-task is an estimate of the time required for completion of the assessment task and is subject to individual variation.

3 An automatic short extension is available for some assessments. Apply through the Service Connect Portal.

Delivery and Resources

Classes 

Each week has two hours of lectures and two hours of workshops. For details of days, times and rooms consult your timetable, by visiting Class Finder on the homepage of eStudent).

Required and Recommended Texts 

All required and recommended readings will be provided as part of the lecture material. 

Unit Web Page 

The unit web page will be hosted in iLearn. You will need to log in to iLearn using your Student One ID and password. The unit will make extensive use of discussion boards also hosted in iLearn. Please post questions there, they will be monitored by the staff on the unit. 

Week 1 Classes

Week 1 includes a two-hour lecture from 14:00 to 16:00 on Tuesday, February 24th, 2026. There will be no practical workshops during the first week.

Methods of Communication 

We will communicate with you via your university email or through announcements in iLearn. Questions to convenors can either be placed on the iLearn discussion board or sent to the unit convenor from your university email address. 

Technology Used and Required

We will make use of a range of modules that are available via the Anaconda Python distribution. We will introduce the relevant modules in the workshops as required. 

This software is installed in the labs; you may also want to ensure that you have working copies of all the above on your own machine. Note that some of this software requires Internet access.

Many packages come in various versions; to avoid potential incompatibilities, you should install versions as close as possible to those used in the labs.

Unit Schedule

Week Topic Reading
1-4 Deep Generative Models (PGMs, AR Models, VAE, Diffusion Models) Lecturer Supplied
5-8 Graph Neural Networks Lecturer Supplied
9-12 Deep Reinforcement Learning Lecturer Supplied
13 Review Lecturer Supplied

Policies and Procedures

Macquarie University policies and procedures are accessible from Policy Central (https://policies.mq.edu.au). Students should be aware of the following policies in particular with regard to Learning and Teaching:

Students seeking more policy resources can visit Student Policies (https://students.mq.edu.au/support/study/policies). It is your one-stop-shop for the key policies you need to know about throughout your undergraduate student journey.

To find other policies relating to Teaching and Learning, visit Policy Central (https://policies.mq.edu.au) and use the search tool.

Student Code of Conduct

Macquarie University students have a responsibility to be familiar with the Student Code of Conduct: https://students.mq.edu.au/admin/other-resources/student-conduct

Results

Results published on platform other than eStudent, (eg. iLearn, Coursera etc.) or released directly by your Unit Convenor, are not confirmed as they are subject to final approval by the University. Once approved, final results will be sent to your student email address and will be made available in eStudent. For more information visit connect.mq.edu.au or if you are a Global MBA student contact globalmba.support@mq.edu.au

Academic Integrity

At Macquarie, we believe academic integrity – honesty, respect, trust, responsibility, fairness and courage – is at the core of learning, teaching and research. We recognise that meeting the expectations required to complete your assessments can be challenging. So, we offer you a range of resources and services to help you reach your potential, including free online writing and maths support, academic skills development and wellbeing consultations.

Student Support

Macquarie University provides a range of support services for students. For details, visit http://students.mq.edu.au/support/

Academic Success

Academic Success provides resources to develop your English language proficiency, academic writing, and communication skills.

The Library provides online and face to face support to help you find and use relevant information resources. 

Student Services and Support

Macquarie University offers a range of Student Support Services including:

Student Enquiries

Got a question? Ask us via the Service Connect Portal, or contact Service Connect.

IT Help

For help with University computer systems and technology, visit http://www.mq.edu.au/about_us/offices_and_units/information_technology/help/. 

When using the University's IT, you must adhere to the Acceptable Use of IT Resources Policy. The policy applies to all who connect to the MQ network including students.

Unit information based on version 2026.03 of the Handbook