Key facts
UNE unit code: COSC551
*You are viewing the 2025 version of this unit which may be subject to change in future.
- Trimester 1 - On Campus
- Trimester 1 - Online
- Armidale Campus
- Yes
- No
- Yes
- 6
Unit information
Deep learning is one of the most important techniques in Artificial Intelligence, underpinning rapidly advancing innovative technologies such as autonomous systems, biometrics, cybersecurity and digital assistance. This unit introduces you to deep learning using a range of toolkits and technologies commonly applied within industry and research settings. You will gain invaluable hands-on experience building deep learning workflows to solve computer vision and natural language processing problems using advanced techniques. Topics covered include computer vision, natural language processing and generative AI, using Deep Convolutional Neural Networks (DCNNs), Transformers, Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs) and Generative Pre-trained Transformers (GPT). You will understand the theoretical concepts underpinning deep learning best practices, with a strong focus on applied skills. The unit culminates in self-directed deep learning project applying knowledge and skills learned.
Offerings
For further information about UNE's teaching periods, please go to Principal Dates.
Teaching period | Mode/location |
---|---|
Trimester 1 | On Campus, Armidale Campus |
Trimester 1 | Online |
*Offering is subject to availability
Intensive schools
There are no intensive schools required for this unit.
Enrolment rules
Notes
Please refer to the student handbook for current details on this unit.
Unit coordinator(s)
Learning outcomes
Upon completion of this unit, students will be able to:
- explain the fundamentals of deep learning including tensors and their operations, gradient descent and backpropagation;
- solve complex problems using a range of deep learning toolkits and technologies commonly applied within industry and research settings;
- analyse and interpret advanced deep learning principles and apply deep convolutional neural networks to computer vision tasks;
- apply advanced principles of deep learning using transformers for natural language processing;
- design and implement an effective deep learning workflow to solve problems using advanced deep learning techniques, applying best practices; and
- demonstrate effective oral communication skills to justify decisions and approach to solving a complex deep learning problem.
Assessment information
Assessments are subject to change up to 8 weeks prior to the start of the teaching period in which you are undertaking the unit.
Title | Must Complete | Weight | Offerings | Assessment Notes |
---|---|---|---|---|
Assignment 1: Deep Convolutional Neural Networks for Computer Vision. | Yes | 15% | All offerings | Students build a computer vision workflow demonstrating understanding of DCNNs. Students record a video demonstration of their workflow and justification of implementation decisions, with reference to best practices and deep learning principles. |
Assignment 2: Transformers for Natural Language Processing. | Yes | 15% | All offerings | Students build a natural language processing workflow demonstrating understanding of transformers. Students record a video demonstration of their workflow and justification of implementation decisions, with reference to best practices deep learning principles. |
Individual Student Project | Yes | 40% | All offerings | Students design and implement a custom workflow to solve a complex problem of their choosing using computer vision AND natural language processing techniques. Students record a short video demonstrating their workflow, explaining how they solved the problem and justifying their implementation choices. |
Open Book Exam | Yes | 30% | All offerings | Open Book Moodle quiz. It is mandatory to pass this component in order to pass the unit. |
Learning resources
Textbooks are subject to change up to 8 weeks prior to the start of the teaching period in which you are undertaking the unit.
Note: Students are expected to purchase prescribed material. Please note that textbook requirements may vary from one teaching period to the next.
Deep Learning with Python
ISBN: 9781617296864
François Chollet, 2nd
Text refers to: All offerings
A five-star experience
Five Stars,
18 Years in a Row
UNE is the only public uni in Australia awarded 18 straight years of five stars for Overall Experience
Good Universities Guide 2007-2024No.1 in NSW for
Student Experience
QILT (government-endorsed) ranks UNE as the top public NSW uni for Student Experience
QILT Student Experience SurveyFive Stars for
Teaching Quality
UNE rates among the top 20 per cent of universities in Australia for Teaching Quality
Good Universities Guide 2024Studying online
At UNE we know it takes more than just being online to be a great online university. It takes time and experience. We pioneered distance education for working adults back in the 1950s, so we’ve been doing this longer than any other Australian university.
We understand the challenges faced by busy adults studying at home. We know that a vital part of online study is your engagement with the learning community. Communication with your classmates, teaching staff and university support staff will enhance your study experience and ensure that your skills extend beyond the subject matter. UNE’s teaching staff are experts in their field which is why UNE consistently receives five stars from students for teaching quality, support and overall experience.*
*The Good Universities Guide
Stay connected
Register your interest and we'll keep you updated
Why study with us?
I'm grateful to UNE for the opportunities studying has given me, but above all, for making me realise I could actually do it, and giving me a sense of accomplishment.
What happens next?
Got any questions about a course you would like to study? Don’t hesitate to contact us, our Future Student team is standing by to help.
2025 applications are now open. The application process only takes 20 minutes to complete. Don’t delay, apply now!
Your start date is based on the study period you choose to apply for.