ECE4179 Neural networks and deep learning
Faculty of Engineering
ECE4179 Neural networks and deep learning is a level 4, 6-credit-point, undergraduate unit from the Faculty of Engineering, offered in 2020 in Semester 2 at Clayton. It needs ENG2005 and ECE2071.
- Credit points
- 6
- Offered in 2020
- Semester 2
- Clayton
- Assessment
- No exam
- 4 tasks
- Workload
- 144 hours
- per semester
This is the 2020 handbook entry. See the 2027 entry.
Reviews
No reviews yetNo reviews yet. Be the first to review ECE4179.
Requisites
Before ECE4179
Prerequisites
Pass these before you enrol.
After ECE4179
No unit lists ECE4179 as a prerequisite in the 2020 handbook.
Enrolment rules
Prerequisites: Or ENG2092 in place of ENG2005
Overview
This unit introduces fundamentals of deep learning and how it can solve problems in many areas, such as image classification, filter design and natural language processing. Neural networks are first described and how training can be achieved with backpropagation. Various forms of deep neural networks are developed, such as multilayer perceptrons, convolution neural networks and recurrent neural networks. The mathematics of stochastic optimisation is used to interpret and understand the behaviour and training of these networks. Programming approaches are discussed for training and deploying neural networks. Deep learning technologies and design examples are discussed in areas such as driverless cars, personal cognitive assistants and mastering of games such as GO.
Offerings in 2020
| Teaching period | Campus | Mode |
|---|---|---|
| Second semester | Clayton | On campus |
Assessment
- AssignmentsThreshold hurdle30%
- QuizzesThreshold hurdle10%
- Course ProjectThreshold hurdle10%
- Final assessmentThreshold hurdle50%
Learning outcomes
When you finish this unit, you should be able to:
- 1
Describe concepts and fundamentals of deep learning, such as the backpropagation algorithm and adversarial learning.
- 2
Discern and appreciate various forms of deep neural networks, such as multilayer perceptrons, convolution neural networks and recurrent neural networks.
- 3
Interpret and apply the mathematics of deep learning, such as stochastic optimisation.
- 4
Design deep learning solutions to problems in computer vision, natural language processing and signal processing. Examples are image classification, object detection, sequence modelling and filter design.
- 5
Demonstrate the training and deployment of neural networks using a high level programming language.
- 6
Critically appraise sources of information and contents of scientific publications and choose relevant information.
Workload and teaching
- Laboratories24 hours
- Lectures24 hours
- Practical activities12 hours
- Teaching approachActive learning
- Teaching approachOnline learning
- Teaching approachProblem-based learning
Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of 4-6 hours of scheduled learning activities and 6-8 hours independent study per week. Scheduled activities may include a combination of teacher-directed learning, peer-directed learning and online engagement. Independent study may include associated readings, assessment and preparation for scheduled activities.
Lectures will be delivered online
Practicals will be delivered online
Learning resources
Recommended resources
Textbooks are available online at https://www.d2l.ai and http://www.deeplearningbook.org
Technology resources
Anaconda package: Available at https://www.anaconda.com
PyTorch package: Available for Anaconda at https://pytorch.org
Where it fits
ECE4179 is part of 5 areas of study in the 2020 handbook.
- ECSYSENG01Core electivesElectrical and computer systems engineeringNo reviews yet
- MAEELEC01Technical elective unitsElectrical engineeringNo reviews yet
- MECHENG01Clayton offeringsMechanical engineeringNo reviews yet
- MAEMEDIC01Technical electivesMedical engineeringNo reviews yet
- ROBMCTRN01Artificial intelligence streamRobotics and mechatronics engineeringNo reviews yet
Contacts
- Chief Examiners
- Dr Mehrtash Tafazzoli Harandi
- Unit Coordinators
- Dr Mehrtash Tafazzoli Harandi
Common questions
What are the prerequisites for ECE4179?
You need ENG2005 and ECE2071 before you enrol. Enrolment rules also apply.
When is ECE4179 offered?
In 2020, ECE4179 runs in Semester 2 at Clayton.
How much work is ECE4179?
The handbook expects about 144 hours of study across the semester. No students have rated its difficulty yet.
Does ECE4179 have an exam?
No. ECE4179 has 4 assessment tasks and no exam.
Which majors and minors include ECE4179?
ECE4179 is part of Electrical and computer systems engineering; Electrical engineering; Mechanical engineering; Medical engineering; and Robotics and mechatronics engineering.