UnitLevel 5Postgraduate

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 2027 in Semester 1 and Semester 2 at Suzhou (SEU), Clayton and Malaysia. It needs (FIT9136 or FIT9133) and (MAT9004 or EPM5026) and unlocks 3 units.

Credit points
6
Offered in 2027
Semester 1, Semester 2
Suzhou (SEU), Clayton, Malaysia
Assessment
Exam 80%
and 7 other tasks
Workload
144 hours
per semester

Reviews

No reviews yet

No reviews yet. Be the first to review FIT5215.

Requisites

Enrolment rules

Prerequisite: For students enrolled in E3001, E3002, E3005, E3010, E3011, E3007 completing the Software Engineering specialisation: FIT2085

Overview

Modern machine learning provides core underlying theory and techniques to data science and artificial intelligence. This unit is for you 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 2027

Teaching periodCampusMode
First semesterSuzhou (SEU)On campus
Second semesterClaytonFlexible
Second semesterMalaysiaOn campus

Assessment

  • Assignment 1Artefact
    20%
  • In class test 1Quiz / Test
    10%
  • In class test 2Quiz / Test
    10%
  • Assignment 2Artefact
    20%
  • Scheduled final assessment (2 hours and 10 minutes)Examination
    40%
  • Assessment 1aArtefact
    20%
  • Assessment 1bQuiz / Test
    20%
  • Assessment 2Artefact
    20%
  • Scheduled final assessment (2 hours and 10 minutes)Examination
    40%

Assessment details may change. Please refer to the assessment information in Moodle closer to the start of the teaching period.

Learning outcomes

When you finish this unit, you should be able to:

  1. 1

    Describe the life cycle of a machine leaning system, what is involved in designing such systems and strategy to maintain them;

  2. 2

    Describe what deep learning (DL) is, access what makes DL work or fail and where they should be applied;

  3. 3

    Develop and apply deep neural networks, convolutional neural networks, recurrent neural networks and different optimisation strategies for training them;

  4. 4

    Develop unsupervised feature learning models and representation learning models.

Workload and teaching

  • Laboratories20 hours
  • Laboratories24 hours
  • Lectures20 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 teaching activities.

Learning resources

Required resources

Hands-on Machine Learning with Scikit-Learn and TensorFlow (Aurelien Geron), 2017

Deep Learning (Ian Goodfellow, Yoshua Bengio and Aaron Courville), MIT Press, 2016

Where it fits

FIT5215 is part of 2 areas of study in the 2027 handbook.

Contacts

Chief Examiners
Dr Trung Le
Unit Coordinators
Dr Arghya Pal

Common questions

What are the prerequisites for FIT5215?

You need (FIT9136 or FIT9133) and (MAT9004 or EPM5026) before you enrol. Enrolment rules also apply.

What can I take after FIT5215?

FIT5215 is a prerequisite or corequisite for 3 units, including FIT5216, FIT5217 and FIT5221.

When is FIT5215 offered?

In 2027, FIT5215 runs in Semester 1 and Semester 2 at Suzhou (SEU), Clayton and Malaysia.

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 80% of the final mark, alongside 8 other tasks.

Which majors and minors include FIT5215?

FIT5215 is part of Computational science and Software engineering.

More details

Credit points
6
Level
5
Study level
Postgraduate
Faculty
Faculty of Information Technology
Type
Coursework
EFTSL
0.125
Student contribution
SCA Band 2
Study abroad
Available