Skip to main content
Unit outline_

COMP5328: Advanced Machine Learning

Semester 2, 2021 [Normal evening] - Remote

Machine learning models explain and generalise data. This course introduces some fundamental machine learning concepts, learning problems and algorithms to provide understanding and simple answers to many questions arising from data explanation and generalisation. For example, why do different machine learning models work? How to further improve them? How to adapt them to different purposes? The fundamental concepts, learning problems and algorithms are carefully selected. Many of them are closely related to practical questions of the day, such as transfer learning, learning with label noise and multi-view learning.

Unit details and rules

Academic unit Computer Science
Credit points 6
Prerequisites
? 
None
Corequisites
? 
COMP5318 OR COMP3308 OR COMP3608
Prohibitions
? 
None
Assumed knowledge
? 

None

Available to study abroad and exchange students

No

Teaching staff

Coordinator Tongliang Liu, tongliang.liu@sydney.edu.au
Type Description Weight Due Length
Final exam (Take-home short release) Type D final exam hurdle task Final exam
Written examination
50% Formal exam period 3 hours (including reading time)
Outcomes assessed: LO1 LO2 LO3 LO4 LO5 LO6 LO7 LO8
Assignment group assignment Assignment 1
Written report
25% Week 09 4 weeks
Outcomes assessed: LO1 LO2 LO3 LO4 LO5 LO6 LO7 LO8
Assignment group assignment Assignment 2
Written report
25% Week 13 4 weeks
Outcomes assessed: LO1 LO2 LO3 LO4 LO5 LO6 LO7 LO8
hurdle task = hurdle task ?
group assignment = group assignment ?
Type D final exam = Type D final exam ?

Assessment summary

Assignments: Demonstrating the knowledge and skills from a given problem description. 

Final exam: The final exam covers all aspects of the course.
 

Assessment criteria

The University awards common result grades, set out in the Coursework Policy 2014 (Schedule 1).

As a general guide, a high distinction indicates work of an exceptional standard, a distinction a very high standard, a credit a good standard, and a pass an acceptable standard.

Result name

Mark range

Description

High distinction

85 - 100

 

Distinction

75 - 84

 

Credit

65 - 74

 

Pass

50 - 64

 

Fail

0 - 49

When you don’t meet the learning outcomes of the unit to a satisfactory standard.

It is a policy of the School of Computer Science that in order to pass this unit, a student must achieve at least 40% in the written examination. For subjects without a final exam, the 40% minimum requirement applies to the corresponding major assessment component specified by the lecturer. A student must also achieve an overall final mark of 50 or more. Any student not meeting these requirements may be given a maximum final mark of no more than 45 regardless of their average.

 

For more information see guide to grades.

Late submission

In accordance with University policy, these penalties apply when written work is submitted after 11:59pm on the due date:

  • Deduction of 5% of the maximum mark for each calendar day after the due date.
  • After ten calendar days late, a mark of zero will be awarded.

This unit has an exception to the standard University policy or supplementary information has been provided by the unit coordinator. This information is displayed below:

A penalty of 5% per day late, e.g.: o A good assignment that would normally get 9/10 and is 2 days late loses 10% of the full 10 marks, i.e. new mark = 8/10. An average assignment that would normally get 5/10 and is 5 days late loses 25% of the full 10 marks, i.e. new mark = 2.5/10. Assignments more than 5 days late get 0. Late submissions for online quiz are not accepted.

Academic integrity

The Current Student website provides information on academic integrity and the resources available to all students. The University expects students and staff to act ethically and honestly and will treat all allegations of academic integrity breaches seriously.

We use similarity detection software to detect potential instances of plagiarism or other forms of academic integrity breach. If such matches indicate evidence of plagiarism or other forms of academic integrity breaches, your teacher is required to report your work for further investigation.

Use of generative artificial intelligence (AI) and automated writing tools

You may only use generative AI and automated writing tools in assessment tasks if you are permitted to by your unit coordinator. If you do use these tools, you must acknowledge this in your work, either in a footnote or an acknowledgement section. The assessment instructions or unit outline will give guidance of the types of tools that are permitted and how the tools should be used.

Your final submitted work must be your own, original work. You must acknowledge any use of generative AI tools that have been used in the assessment, and any material that forms part of your submission must be appropriately referenced. For guidance on how to acknowledge the use of AI, please refer to the AI in Education Canvas site.

The unapproved use of these tools or unacknowledged use will be considered a breach of the Academic Integrity Policy and penalties may apply.

Studiosity is permitted unless otherwise indicated by the unit coordinator. The use of this service must be acknowledged in your submission as detailed on the Learning Hub’s Canvas page.

Outside assessment tasks, generative AI tools may be used to support your learning. The AI in Education Canvas site contains a number of productive ways that students are using AI to improve their learning.

Simple extensions

If you encounter a problem submitting your work on time, you may be able to apply for an extension of five calendar days through a simple extension.  The application process will be different depending on the type of assessment and extensions cannot be granted for some assessment types like exams.

Special consideration

If exceptional circumstances mean you can’t complete an assessment, you need consideration for a longer period of time, or if you have essential commitments which impact your performance in an assessment, you may be eligible for special consideration or special arrangements.

Special consideration applications will not be affected by a simple extension application.

Using AI responsibly

Co-created with students, AI in Education includes lots of helpful examples of how students use generative AI tools to support their learning. It explains how generative AI works, the different tools available and how to use them responsibly and productively.

WK Topic Learning activity Learning outcomes
Week 01 Introduction to Machine Learning Problems Lecture (2 hr) LO1 LO3 LO4 LO6
Week 02 Introduction to Machine Learning Problems Tutorial (1 hr) LO1 LO3 LO4 LO6
Loss Functions and Convex Optimisation Lecture (2 hr) LO1 LO3 LO4 LO6 LO7
Week 03 Loss Functions and Convex Optimisation Tutorial (1 hr) LO1 LO3 LO4 LO6 LO7
Hypothesis Complexity and Generalisation Lecture (2 hr) LO1 LO2 LO3 LO4 LO6 LO7 LO8
Week 04 Online quiz Performance (1 hr) LO1 LO2 LO3 LO4 LO6 LO7 LO8
Week 05 Hypothesis Complexity and Generalisation Tutorial (1 hr) LO1 LO2 LO3 LO4 LO6 LO7 LO8
Dictionary Learning and NMF Lecture (2 hr) LO1 LO3 LO4 LO5 LO6 LO7 LO8
Week 06 Sparse Coding and Regularisation Lecture (2 hr) LO1 LO2 LO3 LO4 LO5 LO6 LO7 LO8
Dictionary Learning and NMF Tutorial (1 hr) LO1 LO3 LO4 LO5 LO6 LO7 LO8
Week 07 Learning with Noisy Data Lecture (2 hr) LO1 LO2 LO3 LO4 LO6 LO7 LO8
Sparse Coding and Regularisation Tutorial (1 hr) LO1 LO2 LO3 LO4 LO5 LO6 LO7 LO8
Week 08 Domain Adaptation and Transfer Learning Lecture (2 hr) LO1 LO2 LO3 LO4 LO6 LO7 LO8
Learning with Noisy Data Tutorial (1 hr) LO1 LO2 LO3 LO4 LO6 LO7 LO8
Week 09 Learning with Noisy Data II: Label Noise Lecture (2 hr) LO1 LO2 LO3 LO4 LO5 LO6 LO7 LO8
Domain Adaptation and Transfer Learning Tutorial (1 hr) LO1 LO2 LO3 LO4 LO6 LO7 LO8
Week 10 Reinforcement Learning Lecture (2 hr) LO1 LO3 LO4 LO6 LO7 LO8
Learning with Noisy Data II: Label Noise Tutorial (1 hr) LO1 LO2 LO3 LO4 LO5 LO6 LO7 LO8
Week 11 Causal Inference Lecture (2 hr) LO3 LO4 LO6 LO7
Reinforcement Learning Tutorial (1 hr) LO1 LO3 LO4 LO6 LO7 LO8
Week 12 Multi-task Learning Lecture (2 hr) LO1 LO3 LO4 LO6 LO7 LO8
Causal Inference Tutorial (1 hr) LO3 LO4 LO6 LO7
Week 13 Review Lecture (2 hr) LO1 LO2 LO3 LO4 LO5 LO6 LO7 LO8
Multi-task Learning Tutorial (1 hr) LO1 LO3 LO4 LO6 LO7 LO8

Study commitment

Typically, there is a minimum expectation of 1.5-2 hours of student effort per week per credit point for units of study offered over a full semester. For a 6 credit point unit, this equates to roughly 120-150 hours of student effort in total.

Learning outcomes are what students know, understand and are able to do on completion of a unit of study. They are aligned with the University's graduate qualities and are assessed as part of the curriculum.

At the completion of this unit, you should be able to:

  • LO1. Present the design and evaluation of a machine learning algorithm, describing the design processes and evaluation
  • LO2. Understand the variance and bias trade-off in machine learning algorithms
  • LO3. Understand and analyse some machine learning algorithms and have some knowledge to further improve them
  • LO4. Understand and analyse some machine learning problems and have some knowledge to adapt the existing machine learning models to different purposes
  • LO5. Implement machine learning algorithms from peer-reviewed papers
  • LO6. Understand the nature of the statistical foundations of designing or adapting learning algorithms
  • LO7. At the completion of this unit, you should be able to demonstrate knowledge of the introduced machine learning models and the relative strengths and weaknesses of each and their most appropriate uses
  • LO8. At the completion of this unit, you should be able to demonstrate knowledge of methods to analyse machine learning algorithms, such as hypothesis complexities and generalisation bounds.

Graduate qualities

The graduate qualities are the qualities and skills that all University of Sydney graduates must demonstrate on successful completion of an award course. As a future Sydney graduate, the set of qualities have been designed to equip you for the contemporary world.

GQ1 Depth of disciplinary expertise

Deep disciplinary expertise is the ability to integrate and rigorously apply knowledge, understanding and skills of a recognised discipline defined by scholarly activity, as well as familiarity with evolving practice of the discipline.

GQ2 Critical thinking and problem solving

Critical thinking and problem solving are the questioning of ideas, evidence and assumptions in order to propose and evaluate hypotheses or alternative arguments before formulating a conclusion or a solution to an identified problem.

GQ3 Oral and written communication

Effective communication, in both oral and written form, is the clear exchange of meaning in a manner that is appropriate to audience and context.

GQ4 Information and digital literacy

Information and digital literacy is the ability to locate, interpret, evaluate, manage, adapt, integrate, create and convey information using appropriate resources, tools and strategies.

GQ5 Inventiveness

Generating novel ideas and solutions.

GQ6 Cultural competence

Cultural Competence is the ability to actively, ethically, respectfully, and successfully engage across and between cultures. In the Australian context, this includes and celebrates Aboriginal and Torres Strait Islander cultures, knowledge systems, and a mature understanding of contemporary issues.

GQ7 Interdisciplinary effectiveness

Interdisciplinary effectiveness is the integration and synthesis of multiple viewpoints and practices, working effectively across disciplinary boundaries.

GQ8 Integrated professional, ethical, and personal identity

An integrated professional, ethical and personal identity is understanding the interaction between one’s personal and professional selves in an ethical context.

GQ9 Influence

Engaging others in a process, idea or vision.

Outcome map

Learning outcomes Graduate qualities
GQ1 GQ2 GQ3 GQ4 GQ5 GQ6 GQ7 GQ8 GQ9

This section outlines changes made to this unit following staff and student reviews.

No significant changes have been made since this unit was last offered

IMPORTANT: School policy relating to Academic Dishonesty and Plagiarism.

In assessing a piece of submitted work, the School of Computer Science may reproduce it entirely, may provide a copy to another member of faculty, and/or to an external plagiarism checking service or in-house computer program and may also maintain a copy of the assignment for future checking purposes and/or allow an external service to do so.

Computer programming assignments may be checked by specialist code similarity detection software. The Faculty of Engineering currently uses the MOSS similarity detection engine (see http://theory.stanford.edu/~aiken/moss/), or the similarity report available in ED (edstem.org). These programs work in a similar way to TurnItIn in that they check for similarity against a database of previously submitted assignments and code available on the internet, but they have added functionality to detect cases of similarity of holistic code structure in cases such as global search and replace of variable names, reordering of lines, changing of comment lines, and the use of white space.

All written assignments submitted in this unit of study will be submitted to the similarity detecting software program known as Turnitin. Turnitin searches for matches between text in your written assessment task and text sourced from the Internet, published works and assignments that have previously been submitted to Turnitin for analysis.

There will always be some degree of text-matching when using Turnitin. Text-matching may occur in use of direct quotations, technical terms and phrases, or the listing of bibliographic material. This does not mean you will automatically be accused of academic dishonesty or plagiarism, although Turnitin reports may be used as evidence in academic dishonesty and plagiarism decision-making processes.

Work, health and safety

We are governed by the Work Health and Safety Act 2011, Work Health and Safety Regulation 2011 and Codes of Practice. Penalties for non-compliance have increased. Everyone has a responsibility for health and safety at work. The University’s Work Health and Safety policy explains the responsibilities and expectations of workers and others, and the procedures for managing WHS risks associated with University activities.

General laboratory safety rules

  • No eating or drinking is allowed in any laboratory under any circumstances 
  • A laboratory coat and closed-toe shoes are mandatory 
  • Follow safety instructions in your manual and posted in laboratories 
  • In case of fire, follow instructions posted outside the laboratory door 
  • First aid kits, eye wash and fire extinguishers are located in or immediately outside each laboratory 
  • As a precautionary measure, it is recommended that you have a current tetanus immunisation. This can be obtained from University Health Service: unihealth.usyd.edu.au/

Disclaimer

The University reserves the right to amend units of study or no longer offer certain units, including where there are low enrolment numbers.

To help you understand common terms that we use at the University, we offer an online glossary.