COMP5329: Semester 1, 2022

University home

Library

Current students

Staff intranet

Find an event

Give

Current students

Units COMP5329 Semester 1 2022 [Normal evening]

Unit of study_

COMP5329: Deep Learning

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.

Details

Academic unit	Computer Science
Unit code	COMP5329
Unit name	Deep Learning
Session, year ?	Semester 1, 2022
Attendance mode	Normal evening
Location	Remote
Credit points	6

Enrolment rules

Prohibitions ?	None
Prerequisites ?	None
Corequisites ?	None
Assumed knowledge ?	COMP5318
Available to study abroad and exchange students	Yes

Teaching staff and contact details

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

Type	Description	Weight	Due	Length
Final exam (Record+)	Final exam Exam on Canvas	60%	Formal exam period	2 hours
Outcomes assessed:
Assignment	Assignment 1 take-home assignment.	20%	Week 07	n/a
Outcomes assessed:
Assignment	Assignment 2 take-home assignment.	20%	Week 12	n/a
Outcomes assessed:
= group assignment ? = Type B final exam ?

Assignment 1 – writing a computer program to solve a given task and a report discussing the results.
Assignment 2 – writing a computer program to solve a given task and a report discussing the results.
Exam – online exam 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 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.

For more information see sydney.edu.au/students/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:

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

Special consideration

If you experience short-term circumstances beyond your control, such as illness, injury or misadventure or if you have essential commitments which impact your preparation or performance in an assessment, you may be eligible for special consideration or special arrangements.

Academic integrity

The Current Student website provides information on academic honesty, academic dishonesty, 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 dishonesty or plagiarism seriously.

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

Weekly schedule

WK	Topic	Learning activity
Week 01	Introduction	Lecture and tutorial (3 hr)
Week 02	Multilayer neural networks	Lecture and tutorial (3 hr)
Week 03	Optimization for Deep Models	Lecture and tutorial (3 hr)
Week 04	Regularization for Deep Models	Lecture and tutorial (3 hr)
Week 05	Convolutional Neural Networks	Lecture and tutorial (3 hr)
Week 06	Neural Network Architectures	Lecture and tutorial (3 hr)
Week 07	Recurrent Neural Networks	Lecture and tutorial (3 hr)
Week 09	Transformer Neural Networks	Lecture and tutorial (3 hr)
Week 10	Graph Convolutional Networks	Lecture and tutorial (3 hr)
Week 11	Deep Learning Applications	Lecture and tutorial (3 hr)
Week 12	Deep Generation Models	Lecture and tutorial (3 hr)
Week 13	Review	Lecture and tutorial (3 hr)

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.

Required readings

All readings for this unit can be accessed through the Library eReserve, available on Canvas.

Goodfellow I J, Bengio Y, Courville A, Deep Learning. MIT Press, 2016.

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.

Outcomes
Graduate qualities

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’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
Learning outcomes

Closing the loop

- Balance the introduction on theoretical foundations and practical uses of deep learning.

Key dates
Key dates through the academic year, including teaching periods, census, payment deadlines and exams.
Student administration
Enrolment, course planning, fees, graduation, support services, student IT
Expectations of student conduct
Code of Conduct for Students, Conditions of Enrollment, University Privacy Statement, Academic Integrity
Academic appeals
Academic appeals process, special consideration, rules and guidelines, advice and support
Learning and teaching policy
Policy register, policy search
Financial support
Scholarships, interest free loans, bursaries, money management
Study resources
Learning Centre, faculty and school programs, Library, online resources
Health and support
Student Centre, counselling & psychological services, University Health Service, general health and wellbeing

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.

Current students

Overview

Details

Enrolment rules

Teaching staff and contact details

Assessment

Assessment criteria

Late submission

Special consideration

Academic integrity

Weekly schedule

Study commitment

Required readings

Learning outcomes

Graduate qualities

Outcome map

Closing the loop

Disclaimer

On this page

Useful links

Media

Student links

About us

Connect