Outline

Overview

This course provides an introduction to deep machine learning, which is rapidly emerging as one of the most successful and widely applicable set of techniques across a range of applications. Students taking this course will be exposed to cutting-edge research in machine learning, starting from theories, models, and algorithms, to implementation and recent progress of deep learning. Specific topics include: classical architectures of deep neural network, optimization techniques for training deep neural networks, theoretical understanding of deep learning, and diverse applications of deep learning in computer vision.

Unit details and rules

Academic unit	Computer Science
Credit points	6
Prerequisites ?	(DATA3888 or COMP3888 or COMP3988 or CSEC3888 or ISYS3888 or SOFT3888 or ENGG3112 or SCPU3001) and (COMP3308 or COMP3608 or COMP4318 or BMET2925)
Corequisites ?	None
Prohibitions ?	COMP5329 or OCMP5329
Assumed knowledge ?	A major in a computer science area
Available to study abroad and exchange students	Yes

Teaching staff

Coordinator	Chang Xu, c.xu@sydney.edu.au

Assessment

The census date for this unit availability is 31 March 2026

Details
Criteria

Type	Description	Weight	Due	Length	Use of AI
Written exam	Final Exam Supervised final exam	60%	Formal exam period	2 hours	AI prohibited
Outcomes assessed:
Experimental design	Assignment 1 take-home assignment.	20%	Week 07 Due date: 13 Apr 2026 at 23:59	n/a	AI allowed
Outcomes assessed:
Written work	Assignment 2 take-home assignment.	20%	Week 12 Due date: 24 May 2026 at 23:59	n/a	AI allowed
Outcomes assessed:
= group assignment ?

Assessment summary

Assignment 1 鈥� Students will implement specified deep learning methods to solve a structured task and submit a report discussing the methodology and results.

Assignment 2 鈥� Students will propose a well-justified deep learning task, implement a computer program as a solution, and submit a report evaluating the approach and results.

Exam 鈥� A written exam will be held at the end of the semester (less than 40% is automatically a FAIL)

Detailed information for each assessment can be found on Canvas.

Assessment criteria

The University awards common result grades, set out in the听听(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	听
Distinction	75 - 84	听
Credit	65 - 74	听
Pass	50 - 64	听
Fail	0 - 49	When you don鈥檛 meet the learning outcomes of the unit to a satisfactory standard.

听

For more information see guide to grades.

Use of generative artificial intelligence (AI)

You can use generative AI tools for open assessments. Restrictions on AI use apply to secure, supervised assessments used to confirm if students have met specific learning outcomes.

Refer to the assessment table above to see if AI is allowed, for assessments in this unit and check Canvas for full instructions on assessment tasks and AI use.

If you use AI, you must always acknowledge it. Misusing AI may lead to a breach of the听Academic Integrity Policy.

Visit the听Current Students website听for more information on AI in assessments, including听details on how to acknowledge its use.

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:

Assignment 1 and Assignment 2 - late submissions are allowed up to 10 calendar days late. A penalty of 5% per day late will apply.

Academic integrity

The University expects students to act ethically and honestly and will treat all allegations of academic integrity breaches seriously.

Our website听provides information on academic integrity and the resources available to all students. This includes advice on how to avoid common breaches of academic integrity. Ensure that you have completed the听Academic Honesty Education Module (AHEM)听which is mandatory for all commencing coursework students

Penalties for serious breaches can significantly impact your studies and your career after graduation. It is important that you speak with your unit coordinator if you need help with completing assessments.

Visit the听Current Students website听for more information on AI in assessments, including听details on how to acknowledge its use.

Learning support

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听simple extension.鈥� 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鈥檛 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听special consideration or special arrangements.

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

Using AI responsibly

Co-created with students,听听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.

Support for students

The Support for Students Policy听reflects the University鈥檚 commitment to supporting students in their academic journey and making the University safe for students. It is important that you read and understand this policy so that you are familiar with the range of support services available to you and understand how to engage with them.

The University uses email as its primary source of communication with students who need support under the Support for Students Policy. Make sure you check your University email regularly and respond to any communications received from the University.

Learning resources and detailed information about weekly assessment and learning activities can be accessed via Canvas. It is essential that you visit your unit of study Canvas site to ensure you are up to date with all of your tasks.

If you are having difficulties completing your studies, or are feeling unsure about your progress, we are here to help. You can access the support services offered by the University at any time:

Support and Services (including health and wellbeing services, financial support and learning support)
Course planning and administration
Meet with an Academic Adviser

Weekly schedule

WK	Topic	Learning activity
Week 01	Introduction	Lecture (2 hr)
Week 01	Introduction	Tutorial (1 hr)
Week 02	Multilayer Neural Networks & Optimisation	Lecture (2 hr)
Week 02	Multilayer Neural Networks & Optimisation	Tutorial (1 hr)
Week 03	Regularisation in Deep Learning	Lecture (2 hr)
Week 03	Regularisation in Deep Learning	Tutorial (1 hr)
Week 04	Convolutional Neural Networks	Lecture (2 hr)
Week 04	Convolutional Neural Networks	Tutorial (1 hr)
Week 05	Graph Neural Networks	Lecture (2 hr)
Week 05	Graph Neural Networks	Tutorial (1 hr)
Week 07	RNNs and Transformers	Lecture (2 hr)
Week 07	RNNs and Transformers	Tutorial (1 hr)
Week 08	Beyond Transformer Architectures	Lecture (2 hr)
Week 08	Beyond Transformer Architectures	Tutorial (1 hr)
Week 09	Multimodal Foundation Models	Lecture (2 hr)
Week 09	Multimodal Foundation Models	Tutorial (1 hr)
Week 10	Deep Reinforcement Learning	Lecture (2 hr)
Week 10	Deep Reinforcement Learning	Tutorial (1 hr)
Week 11	Self-Supervised Representation Learning	Lecture (2 hr)
Week 11	Self-Supervised Representation Learning	Tutorial (1 hr)
Week 12	Deep Generative Models	Lecture (2 hr)
Week 12	Deep Generative Models	Tutorial (1 hr)
Week 13	Review	Lecture (2 hr)
Week 13	Review	Tutorial (1 hr)

高清福利片 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

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. demonstrate knowledge of the broad range of deep learning applications, such as image classification, object detection, image segmentation and face recognition
LO2. use deep learning software to create deep learning prototypes
LO3. evaluate deep learning algorithms
LO4. demonstrate knowledge of the main methods of deep neural network design and evaluation and the relative strengths and weaknesses of each, and their most appropriate uses
LO5. model application problems as deep learning problems
LO6. apply and tailor known deep learning algorithms for solving new challenging problems
LO7. present the design and evaluation of a deep learning prototype, defining the requirements, describing the design processes and evaluation.

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鈥檚 personal and professional selves in an ethical context.
GQ9	Influence Engaging others in a process, idea or vision.

Outcome map

Learning outcomes	Graduate qualities
Learning outcomes

Alignment with Competency standards

Outcomes	Competency standards
	Engineers Australia Curriculum Performance Indicators - 2.1. Appropriate range and depth of learning in the technical domains comprising the field of practice informed by national and international benchmarks.
	Engineers Australia Curriculum Performance Indicators - 4.3. Proficiency in the engineering design of components, systems and/or processes in accordance with specified and agreed performance criteria.
	Engineers Australia Curriculum Performance Indicators - 4.1. Advanced level skills in the structured solution of complex and often ill defined problems.
	Engineers Australia Curriculum Performance Indicators - 2.4. Advanced knowledge and capability development in one or more specialist areas through engagement with: (a) specific body of knowledge and emerging developments and (b) problems and situations of significant technical complexity.
	Engineers Australia Curriculum Performance Indicators - 4.2. Ability to use a systems approach to complex problems, and to design and operational performance.
	Engineers Australia Curriculum Performance Indicators - 3.3. Creativity and innovation.
	Engineers Australia Curriculum Performance Indicators - 3.1. An ability to communicate with the engineering team and the community at large.

Engineers Australia Curriculum Performance Indicators -

Competency code	Taught, Practiced or Assessed	Competency standard
1.1		Developing underpinning capabilities in mathematics, physical, life and information sciences and engineering sciences, as appropriate to the designated field of practice.
2.1		Appropriate range and depth of learning in the technical domains comprising the field of practice informed by national and international benchmarks.
2.4		Advanced knowledge and capability development in one or more specialist areas through engagement with: (a) specific body of knowledge and emerging developments and (b) problems and situations of significant technical complexity.
3.1		An ability to communicate with the engineering team and the community at large.
3.3		Creativity and innovation.
4.1		Advanced level skills in the structured solution of complex and often ill defined problems.
4.2		Ability to use a systems approach to complex problems, and to design and operational performance.
4.3		Proficiency in the engineering design of components, systems and/or processes in accordance with specified and agreed performance criteria.
5.4		Skills in the selection and application of appropriate engineering resources tools and techniques, appreciation of accuracy and limitations;.

Responding to student feedback

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

The update refreshes the course with recent advances in deep learning.

Disclaimer

Important: the University of Sydney regularly reviews units of study and reserves the right to change the units of study available annually. To stay up to date on available study options, including unit of study details and availability, refer to the relevant handbook.

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

高清福利片

Current students

Overview

Overview

Unit details and rules

Teaching staff

Assessment

Assessment

Assessment summary

Assessment criteria

Use of generative artificial intelligence (AI)

Late submission

Academic integrity

Learning support

Learning support

Simple extensions

Special consideration

Using AI responsibly

Support for students

Weekly schedule

Weekly schedule

高清福利片 commitment

Learning outcomes

Learning outcomes

Graduate qualities

Outcome map

Alignment with Competency standards

Responding to student feedback

Responding to student feedback

Disclaimer

On this page

Useful links

高清福利片

COMP4329: Deep Learning

Semester 1, 2026 [Normal evening] - Camperdown/Darlington, Sydney

Overview

Overview

Unit details and rules

Teaching staff

Assessment

Assessment

Assessment summary

Assessment criteria

Use of generative artificial intelligence (AI)

Late submission

Academic integrity

Learning support

Learning support

Simple extensions

Special consideration

Using AI responsibly

Support for students

Weekly schedule

Weekly schedule

高清福利片 commitment

Learning outcomes

Learning outcomes

Graduate qualities

Outcome map

Alignment with Competency standards

Responding to student feedback

Responding to student feedback

Disclaimer

On this page

Useful links