Credit points: 15

Subject outline

Deep learning is currently the central machine learning method fuelling the artificial intelligence revolution. In this subject you learn how to apply deep learning algorithms to solve real-world problems. This subject does not assume you have previous machine learning experience, therefore it starts teaching deep learning at a very introductory level. You learn how deep learning techniques can be applied to such tasks as image recognition, sentiment classification, machine translation, question and answering, speech synthesis, etc. The practical skills taught in this subject will allow you to build production level deep learning software that can scale out to millions of users. You will be introduced to the popular deep learning programming frameworks of Pytorch and Tensorflow and advanced deep learning techniques such as reinforcement learning, generative adversarial networks and few shot learning.

SchoolEngineering and Mathematical Sciences

Credit points15

Subject Co-ordinatorZhen He

Available to Study Abroad/Exchange StudentsYes

Subject year levelYear Level 5 - Masters

Available as ElectiveNo

Learning ActivitiesN/A

Capstone subjectNo

Subject particulars

Subject rules



Incompatible subjectsN/A

Equivalent subjectsN/A

Quota Management StrategyN/A

Quota-conditions or rulesN/A

Special conditionsN/A

Minimum credit point requirementN/A

Assumed knowledgeN/A

Learning resources

Deep Learning

Resource TypeOther resource

Resource RequirementRecommended

AuthorIan Goodfellow and Yoshua Bengio and Aaron Courville



PublisherMIT Press


Chapter/article titleN/A



Other descriptionN/A

Source locationN/A

Career Ready


Work-based learningNo

Self sourced or Uni sourcedN/A

Entire subject or partial subjectN/A

Total hours/days requiredN/A

Location of WBL activity (region)N/A

WBL addtional requirementsN/A

Graduate capabilities & intended learning outcomes

Graduate Capabilities

Intended Learning Outcomes

01. Analyse the advantages and disadvantages of using traditional machine learning algorithms versus deep learning algorithms for solving industry problems.
02. Analyse a given industry problem and then recommend which deep learning algorithm best solves the problem. This requires the student to know which best learning algorithm is most suitable to solve each type of problem.
03. Write/produce Pytorch code to implement deep learning algorithms to solve computer vision and natural language processing problems.
04. Propose deployment and maintenance strategies for deep learning production systems in the cloud based on the analysis from the machine learning requirements of a business.
05. Given a real-world problem where labels are scarce, investigate different deep learning approaches to tackle this problem.
06. Design the architecture of a generative adversarial network that can generate realistic data.

Subject options

Select to view your study options…

Start date between: and    Key dates

Melbourne (Bundoora), 2021, Semester 1, Day


Online enrolmentYes

Maximum enrolment sizeN/A

Subject Instance Co-ordinatorZhen He

Class requirements

Computer LaboratoryWeek: 11 - 22
One 2.00 hours computer laboratory per week on weekdays during the day from week 11 to week 22 and delivered via face-to-face.

LectureWeek: 10 - 22
One 2.00 hours lecture per week on weekdays during the day from week 10 to week 22 and delivered via face-to-face.


Assessment elementCommentsCategoryContributionHurdle% ILO*

10 laboratory reports(equivalent to 1000 words)Each lab report is equivalent to a 100-word essay amount of work when submitted. Thelab reports will be marked and returned to the students before the start of the following lab.

N/AReportIndividualNo10 SILO3, SILO5

One 2-hour written examination (equivalent to 2000 words)To pass the subject, a pass in the exam is necessary.

N/ACentral examIndividualNo50 SILO1, SILO2, SILO3, SILO4, SILO5, SILO6

Programming Assignment (equivalent to 2500 words)Students will be given at least 4 weeks to do the assignment and the assignment must be submitted electronically.

N/AAssignmentIndividualNo40 SILO3