FIT5215 Deep learning
Faculty of Information Technology
FIT5215 Deep learning is a level 5, 6-credit-point, postgraduate unit from the Faculty of Information Technology, offered in 2020 in Semester 2 at Clayton and Suzhou (SEU). It needs FIT5197 or FIT5047.
- Credit points
- 6
- Offered in 2020
- Semester 2
- Clayton, Suzhou (SEU)
- Assessment
- Exam 40%
- and 1 other task
- 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 FIT5215.
Requisites
Before FIT5215
Prerequisites
Pass these before you enrol.
After FIT5215
No unit lists FIT5215 as a prerequisite in the 2020 handbook.
Overview
Modern machine learning provides core underlying theory and techniques to data science and artificial intelligence. This unit is for students to develop practical knowledge of modern machine learning and deep learning and how they can be used in real-world settings such as image recognition or text clustering via neural embeddings. Learning activities will focus on designing machine learning systems, a broad landscape of supervised and unsupervised learning methods with a focus on modern deep learning knowledge for data analytics including deep neural networks, representation learning and embedding methods, and deep models used for time-series data which are rapidly used in science and industry.
Offerings in 2020
| Teaching period | Campus | Mode |
|---|---|---|
| Second semester | Clayton | On campus |
| Term 3 | Suzhou (SEU) | On campus |
Assessment
- In-semester assessmentThreshold hurdle60%
- Examination (2 hours and 10 minutes)Threshold hurdle40%
Learning outcomes
When you finish this unit, you should be able to:
- 1
Describe the life cycle of a machine leaning system, what is involved in designing such systems and strategy to maintain them;
- 2
Describe what deep learning (DL) is, access what makes DL work or fail and where they should be applied;
- 3
Develop and apply deep neural networks, convolutional neural networks, recurrent neural networks and different optimisation strategies for training them;
- 4
Develop unsupervised feature learning models and representation learning models.
Workload and teaching
- Laboratories24 hours
- Lectures24 hours
- Teaching approachActive learning
Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of scheduled online and face to face learning activities and independent study. Independent study may include associated reading and preparation for scheduled activities. The unit requires on average three/four hours of scheduled activities per week. Scheduled activities may include a combination of teacher directed learning and online engagement.
Where it fits
FIT5215 is part of 1 area of study in the 2020 handbook.
Contacts
- Chief Examiners
- Professor Dinh Phung
Common questions
When is FIT5215 offered?
In 2020, FIT5215 runs in Semester 2 at Clayton and Suzhou (SEU).
How much work is FIT5215?
The handbook expects about 144 hours of study across the semester. No students have rated its difficulty yet.
Does FIT5215 have an exam?
Yes. The exam is worth 40% of the final mark, alongside 1 other task.
Which majors and minors include FIT5215?
FIT5215 is part of Software engineering.