Skip to main content

We are aiming for an incremental return to campus in accordance with guidelines provided by NSW Health and the Australian Government. Until this time, learning activities and assessments will be planned and scheduled for online delivery where possible, and unit-specific details about face-to-face teaching will be provided on Canvas as the opportunities for face-to-face learning become clear.

Unit of study_

ELEC5307: Advanced Signal Processing with Deep Learning

This unit of study introduces deep learning for a broad range of multi-dimensional signal processing applications. It covers deep learning technologies for image super-resolution and restoration, image categorization, object localization, image segmentation, face recognition, person detection and re-identification, human pose estimation, action recognition, object tracking as well as image and video captioning.

Details

Academic unit Electrical and Information Engineering
Unit code ELEC5307
Unit name Advanced Signal Processing with Deep Learning
Session, year
? 
Semester 2, 2020
Attendance mode Normal day
Location Camperdown/Darlington, Sydney
Credit points 6

Enrolment rules

Prohibitions
? 
None
Prerequisites
? 
None
Corequisites
? 
None
Assumed knowledge
? 

Mathematics (e.g., probability and linear algebra) and programming skills (e.g. Matlab/Java/Python/C++)

Available to study abroad and exchange students

Yes

Teaching staff and contact details

Coordinator Luping Zhou, luping.zhou@sydney.edu.au
Type Description Weight Due Length
Final exam (Open book) Type C final exam Final exam
60% Formal exam period 2 hours
Outcomes assessed: LO2 LO3
Assignment Project 1
20% Week 08 n/a
Outcomes assessed: LO1 LO2 LO3 LO4
Assignment Project 2
20% Week 11 n/a
Outcomes assessed: LO1 LO5 LO4 LO3 LO2
Type C final exam = Type C final exam ?

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.

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.

WK Topic Learning activity Learning outcomes
Week 01 Introduction to deep learning (e.g., historical review of machine learning and deep learning, basic machine learning concepts, performance evaluation) Lecture and tutorial (2 hr) LO2
Week 02 Regression Lecture and tutorial (3 hr) LO2
Week 03 Support vector machine Lecture and tutorial (3 hr) LO1 LO2 LO3
Week 04 PCA and LDA Lecture and tutorial (3 hr) LO1 LO2 LO3
Week 05 Back-propagation and optimisation technologies in deep learning Lecture and tutorial (3 hr) LO1 LO2 LO3
Week 06 Network structure Lecture and tutorial (3 hr) LO1 LO2 LO3
Week 07 Guest lecture Lecture and tutorial (3 hr) LO2
Week 08 Probabilistic model Lecture and tutorial (3 hr) LO1 LO2 LO3
Week 09 Structure deep learning Lecture and tutorial (3 hr) LO1 LO2 LO3 LO4
Week 10 Applications of deep learning 1 Lecture and tutorial (3 hr) LO1 LO2 LO3
Week 11 Applications of deep learning 2 Lecture and tutorial (3 hr) LO1 LO2 LO3 LO4 LO5
Week 12 Project presentation Lecture and tutorial (3 hr) LO4 LO5

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.

Prescribed readings

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

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

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. use appropriate software platforms for a given multi-dimensional signal processing task
  • LO2. understand and apply the machine learning and deep learning methods for multi-dimensional signal processing applications
  • LO3. use the existing machine learning and deep learning toolboxes
  • LO4. report results in a professional manner
  • LO5. develop some basic teamwork and project management skills through a group project.

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

Alignment with Competency standards

Outcomes Competency standards
LO1
Engineers Australia Curriculum Performance Indicators - EAPI
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.
Stage 1 Competency Standard for Professional Engineer (AQF9 mapped) - EA
1.3 (L2). Specialist discipline knowledge. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) In-depth understanding of specialist bodies of knowledge within the engineering discipline.
2.2 (L2). Use of engineering techniques, tools and resources. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Techniques, tools and resources.
LO2
Stage 1 Competency Standard for Professional Engineer (AQF9 mapped) - EA
1.2 (L2). Mathematical and computational methods. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Conceptual understanding of the mathematics, numerical analysis, statistics, and computer and information sciences which underpin the engineering discipline.
1.3 (L2). Specialist discipline knowledge. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) In-depth understanding of specialist bodies of knowledge within the engineering discipline.
1.4 (L2). Discipline research knowledge. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Discernment of knowledge development and research directions within the engineering discipline.
2.1 (L2). Complex problem-solving. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Application of established engineering methods to complex engineering problem solving.
2.2 (L2). Use of engineering techniques, tools and resources. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Techniques, tools and resources.
LO3
Stage 1 Competency Standard for Professional Engineer (AQF9 mapped) - EA
1.3 (L2). Specialist discipline knowledge. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) In-depth understanding of specialist bodies of knowledge within the engineering discipline.
2.2 (L3). Use of engineering techniques, tools and resources. (Level 3- Exceeding required standard) Techniques, tools and resources.
LO4
Engineers Australia Curriculum Performance Indicators - EAPI
5.9. Skills in documenting results, analysing credibility of outcomes, critical reflection, developing robust conclusions, reporting outcomes.
Stage 1 Competency Standard for Professional Engineer (AQF9 mapped) - EA
3.2 (L3). Communication. (Level 3- Exceeding required standard) Effective oral and written communication in professional and lay domains.
LO5
Engineers Australia Curriculum Performance Indicators - EAPI
3.1. An ability to communicate with the engineering team and the community at large.
3.4. An understanding of and commitment to ethical and professional responsibilities.
4.3. Proficiency in the engineering design of components, systems and/or processes in accordance with specified and agreed performance criteria.
5.5. Skills in the development and application of mathematical, physical and conceptual models, understanding of applicability and shortcomings.
Stage 1 Competency Standard for Professional Engineer (AQF9 mapped) - EA
2.4 (L2). Engineering project management. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Application of systematic approaches to the conduct and management of engineering projects.
3.2 (L2). Communication. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Effective oral and written communication in professional and lay domains.
3.6 (L2). Team skills. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Effective team membership and team leadership.
Engineers Australia Curriculum Performance Indicators -
Competency code Taught, Practiced or Assessed Competency standard
2.3 T Meaningful engagement with current technical and professional practices and issues in the designated field.
3.6 A An ability to function as an individual and as a team leader and member in multi-disciplinary and multi-cultural teams.
5.5 A Skills in the development and application of mathematical, physical and conceptual models, understanding of applicability and shortcomings.
5.9 A Skills in documenting results, analysing credibility of outcomes, critical reflection, developing robust conclusions, reporting outcomes.
Stage 1 Competency Standard for Professional Engineer (AQF9 mapped) -
Competency code Taught, Practiced or Assessed Competency standard
1.2 (L2) T Mathematical and computational methods. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Conceptual understanding of the mathematics, numerical analysis, statistics, and computer and information sciences which underpin the engineering discipline.
1.2 (L3) T Mathematical and computational methods. (Exceeding required standard) Conceptual understanding of the mathematics, numerical analysis, statistics, and computer and information sciences which underpin the engineering discipline.
1.3 (L2) T Specialist discipline knowledge. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) In-depth understanding of specialist bodies of knowledge within the engineering discipline.
1.3 (L3) T Specialist discipline knowledge. (Level 3- Exceeding required standard) In-depth understanding of specialist bodies of knowledge within the engineering discipline.
1.4 (L2) T Discipline research knowledge. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Discernment of knowledge development and research directions within the engineering discipline.
1.4 (L3) T Discipline research knowledge. (Level 3- Exceeding required standard) Discernment of knowledge development and research directions within the engineering discipline.
1.5 (L2) T Discipline context knowledge. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Knowledge of contextual factors impacting the engineering discipline.
1.5 (L3) T Discipline context knowledge. (Level 3- Exceeding required standard) Knowledge of contextual factors impacting the engineering discipline.
3.2 (L2) A Communication. (Level 2- Attaining required standard (Bachelor Honours standard AQF9)) Effective oral and written communication in professional and lay domains.
No changes have been made since this unit was last offered.

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.