Unit search

Search results

SIT744 - Deep Learning

Year:

2020 unit information

Important Update:

Classes and seminars in Trimester 2/Semester 2, 2020 will be online. Physical distancing for coronavirus (COVID-19) will affect delivery of other learning experiences in this unit. Please check your unit sites for announcements and updates one week prior to the start of your trimester or semester.

Last updated: 2 June 2020

Enrolment modes:Trimester 1: Burwood (Melbourne), Cloud (online)
Trimester 2: Burwood (Melbourne), Cloud (online)
Credit point(s):1
EFTSL value:0.125
Unit Chair:Trimester 1: Wei Luo
Trimester 2: Jianxin Li
Prerequisite:

SIT720 or SIT742

Corequisite:

Nil

Incompatible with:

Nil

Typical study commitment:

Students will on average spend 150 hours over the teaching period undertaking the teaching, learning and assessment activities for this unit.

Scheduled learning activities - campus:

1 x 2 hour class per week, 1 x 1 hour practical per week.

Scheduled learning activities - cloud:

1 x 1 hour scheduled online workshop per week.

Content

Deep learning is a disruptive technology for data science and artificial intelligence. This unit is for students to develop practical knowledge of deep learning and associated applications. Learning activities will focus on understanding deep learning theories, constructing deep learning models for handling structured and unstructured data, such as images, videos, and texts.  Concepts such as computational graphs and representation learning that form core knowledge in this unit will be introduced. Students will also learn about deep learning techniques for data analytics such as convolutional networks, recurrent networks, and neural embedding methods which are being widely adopted in industries. 

 

These are the Learning Outcomes (ULO) for this Unit

At the completion of this Unit
successful
students can:

Deakin Graduate Learning Outcomes

ULO1

Explain deep learning and its role in data science and AI.

GLO1: Discipline-specific knowledge and capabilities
GLO2: Communication

ULO2

Apply deep learning theory to formulate data analytics or artificial intelligence problems.

GLO1: Discipline-specific knowledge and capabilities
GLO4: Critical thinking
GLO5: Problem solving

ULO3

Design suitable deep learning algorithms for unsupervised learning and supervised learning problems.

GLO1: Discipline-specific knowledge and capabilities
GLO3: Digital literacy
GLO4: Critical thinking
GLO5: Problem solving

ULO4

Model and implement algorithms for processing structured and unstructured data, including images
videos, and texts.

GLO1: Discipline-specific knowledge and capabilities
GLO4: Critical thinking
GLO5: Problem solving

These Unit Learning Outcomes are applicable for all teaching periods throughout the year

Assessment

:
Assessment Description Student output Weighting (% total mark for unit) Indicative due week
Problem solving task Written answers, program source codes and outputs 25% Week 5
Project Written answers, program source codes and outputs 40% Week 9
Examination 2-hour written examination 35% Examination period

The assessment due weeks provided may change. The Unit Chair will clarify the exact assessment requirements, including the due date, at the start of the teaching period.

Learning Resource

The texts and reading list for the unit can be found on the University Library via the link below: SIT744 Note: Select the relevant trimester reading list. Please note that a future teaching period's reading list may not be available until a month prior to the start of that teaching period so you may wish to use the relevant trimester's prior year reading list as a guide only.

Unit Fee Information

Click on the fee link below which describes you: