Course Title: Deep Learning

Part A: Course Overview

Course Title: Deep Learning

Credit Points: 12.00

Important Information:

Please note that this course may have compulsory in-person attendance requirements for some teaching activities.

Please check your Canvas course shell closer to when the course starts to see if this course requires mandatory in-person attendance. The delivery method of the course might have to change quickly in response to changes in the local state/national directive regarding in-person course attendance. 


Course Code




Learning Mode

Teaching Period(s)


City Campus


171H School of Science


Sem 2 2020,
Sem 2 2021


City Campus


175H Computing Technologies


Sem 2 2022

Course Coordinator: Dr Ruwan Tennakoon

Course Coordinator Phone: +61 3 9925 3306

Course Coordinator Email:

Course Coordinator Location: 14.11.03

Course Coordinator Availability: By appointment, by email

Pre-requisite Courses and Assumed Knowledge and Capabilities

Enforced Pre-requisite: Computational Machine Learning COSC2793

Course Description

Deep Learning is a field of Machine Learning that focus on large scale neural networks. Deep Networks are suited for solving a variety of complex problems, such as computer vision, natural language processing, and large-scale state estimation. While Deep Networks require vast collections of training data, the networks often outperform humans. Deep Learning has increasingly become a core aspect of both major IT companies and new tech start-ups.

You will undertake a thorough study of the Deep Learning, from its foundations in perceptron’s and multi-layer networks, through to present-day deep architectures including convolutional neural networks. You will critically analyse issues with deep learning, learn how to use open source toolkits, and learn how to critically analyse outputs from these applications. Assessed work will involve real world datasets from a variety of domains.

Objectives/Learning Outcomes/Capability Development

Program Learning Outcomes

The course contributes to the program learning outcomes for MC271 – Master of Artificial Intelligence:


PLO 1: Enabling Knowledge

  • Demonstrate mastery of a body of knowledge that includes recent developments in Artificial Intelligence, Computer Science and information technology;
  • Understand and use appropriate and relevant, fundamental and applied AI knowledge, methodologies and modern computational tools;
  • Recognise and use research principles and methods applicable to Artificial Intelligence.


PLO 2: Critical Analysis

  • Analyse and model complex requirements and constraints for the purpose of designing and implementing software artefacts and IT systems;
  • Evaluate and compare designs of software artefacts and IT systems on the basis of organisational and user requirements;
  • Bring together and flexibly apply knowledge to characterise, analyse and solve a wide range of AI problems.


PLO 3: Problem Solving

  • Design and implement software solutions that accommodate specified requirements and constraints, based on analysis or modelling or requirements specification;
  • Apply an understanding of the balance between the complexity / accuracy of the Artificial techniques used and the timeliness of the delivery of the solution.

Upon successful completion of this course you should be able to:

  • CLO1 Discuss and critically analyse a variety of neural network architectures; Evaluate and Compare approaches andalgorithms on the basis of the nature of the problem/task being addressed.
  • CLO2 Synthesise suitable solutions to address particular machine learning problems based on analysis of the problemand characteristics of the data involved.
  • CLO3 Communicate effectively with a variety of audiences through a range of modes and media, in particular to: inter-pret abstract theoretical propositions, choose methodologies, justify conclusions and defend professional decisionsto both IT and non-IT personnel via technical reports of professional standard and technical presentations.
  • CLO4 Develop skills for further self-directed learning in the general context of neural networks and machine learning;Research, Discuss, and Use new and novel algorithms for solving problems; Adapt experience and knowledge toand from other computer sciences contexts such as artificial intelligence, machine learning, and software design.

Overview of Learning Activities

Teacher Guided Hours (face to face): 48 per semester

Teacher-guided learning will include pre-recorded lecture videos to present main concepts, small-class tutorials to reinforce those concepts, and supervised computer laboratory sessions to support programming practice under guidance from an instructor.


Learner Directed Hours: 72 per semester

Learner-directed hours include time spent reading and studying lecture notes and prescribed text in order to better understand the concepts; working through examples that illustrate those concepts; and performing exercises and assignments designed by the teachers to reinforce concepts and develop practical skills across a variety of problem types.

Overview of Learning Resources

You are encouraged to bring your laptops and use the freely available software to conduct the laboratories.

You will make extensive use of computer laboratories and relevant software provided by the University. You will be able to access course information and learning materials through MyRMIT and Canvas. Lists of relevant reference texts, resources in the library and freely accessible Internet sites will be provided.

Overview of Assessment

This course has no hurdle requirements.

Assessment tasks

Assessment Task 1: (30%)
Introduction to working with typical deep neural network systems, such as Tensor Flow. You will individually solve a real-world data problem, to gain experience and familiarity in the typical process for training, testing, and evaluating the performance of a neural network.
This task supports CLOs: 1, 2, 4

Assessment Task 2: (50%) Major project. You will undertake solving a significant problem on a real-world data set, researching, developing, and implementing their own solution to the problem, both with and without the use existing off-the-shelf solutions.
This task supports CLOs: 1-4 

Exam: (20%) Presentation. You will conduct a virtual presentation presenting a brief summary and critical analysis of the project work that is done in Assessment Task 1/2, as well as improvements/extensions that could be made for your own work based on a literature review of the state-of-the-art approaches. Upon completion of the presentation, you are required to answer a number of follow-up questions related to your project work and studies.
This task supports CLOs: 1-4