Credit points: 15

Subject outline

Quantitative analysis plays an important role in industrial data analytics and knowledge engineering, which makes it very useful to develop computing skills for data regression and classification. This subject covers fundamentals of machine learning techniques in theory and practice. The subject is designed to focus on solving industrial data modelling problems using neural networks. You will learn how to test various learning algorithms and compare performance evaluations. Some advanced machine learning techniques for data classification will also be addressed. You will work with industrial data modeling in labs and assignments to consolidate your knowledge and gain hands-on experience with machine learning applications

SchoolSchool Engineering&Mathematical Sciences

Credit points15

Subject Co-ordinatorNasser Sabar

Available to Study Abroad StudentsYes

Subject year levelYear Level 5 - Masters

Exchange StudentsYes

Subject particulars

Subject rules

Prerequisites CSE3CI or admission into one of the following courses: SMIT, SMICT,SMITCN SMCSC, SGIT, SGCS or SMDS.


Incompatible subjects CSE3CI and CSE4CI and CSE5CI

Equivalent subjectsN/A

Special conditions Students in the following courses are not permitted to enrol: SBCS, SBIT, SBCSGT, SVCSE, SZCSC, SBITP and SBBIY.


Resource TypeTitleResource RequirementAuthor and YearPublisher
ReadingsNeural Networks and Deep LearningRecommendedMichael Nielsen, 2015Determination Press
ReadingsNeural Networks and Learning MachinesRecommendedSimon Haykin, 2009Prentice Hall (3rd edition)

Graduate capabilities & intended learning outcomes

01. Explain associated concepts and applications of machine learning techniques for data analytics.

Lecture 1 is on the introduction of machine learning techniques and its applications in data analytics will be discussed in Lecture 1.

02. Critically identify the major components and system design in developing neural networks data regression and classification.

Linear regression analysis, multilayer perceptrons with the error back-propagation algorithm, random vector functional-link nets, and stochastic configuration networks, support vector machines, and self-organization maps are presented in the lectures 2 through 7 . Basics of deep learning and convolutional neural networks are discussed in lecture 8 to 9.

03. Analyse data to design, implement and evaluate machine learning techniques for real world problem solving.

In lecture 10 and 11 case studies are presented to demonstrate the value and usefulness of machine learning techniques for data analytics.

04. Implement a neural network with different learning algorithms for time- series forecasting with real world data from industry.

Lab 1 and Lab 2 are on the Python basics; Lab 3 to Lab 8 are on neural networks implementation, where students will learn how to use TensorFlow tools to implement a machine learning system for resolving a time-series forecasting problem.

Subject options

Select to view your study options…

Start date between: and    Key dates

Melbourne, 2020, Semester 1, Blended


Online enrolmentYes

Maximum enrolment sizeN/A

Enrolment information

Subject Instance Co-ordinatorNasser Sabar

Class requirements

Lecture Week: 10 - 22
One 2.0 hours lecture per week on weekdays during the day from week 10 to week 22 and delivered via face-to-face.

Laboratory Class Week: 11 - 22
One 2.0 hours laboratory class per week on weekdays during the day from week 11 to week 22 and delivered via face-to-face.


Assessment elementComments% ILO*
Assignment 1 - Assignment report on neural networks for data modeling, 750 words per student.Group project) (equiv to 750 words per students with maximum 4 students20 04
Assignment 2 - Report presentation- 750 words per student. (Group project) (equiv to 750 words per students with maximum 4 students with maximum 4 students30 04
3 hour Exam (equivalent to 3,000 words)50 01, 02, 03