[an error occurred while processing this directive] [an error occurred while processing this directive]
[an error occurred while processing this directive]
[an error occurred while processing this directive]

FIT5186 Intelligent systems - Semester 1, 2013

This unit introduces main techniques widely used in intelligent software systems to students in the Master of Information Technology Systems course with the Network Computing major. Specifically, it focuses on the techniques in relation to network structures. Main topics covered include neural network models, supervised learning and classification, unsupervised learning and clustering, fuzzy logic, intelligent decision analysis, optimum network flow modelling, and recommender systems.

Contact Hours

2 hrs lectures/wk, 2 hrs laboratories/wk

Workload requirements

Students will be expected to spend a total of 12 hours per week during semester on this unit as follows:

Lectures: 2 hours per week
Tutorials/Lab Sessions: 2 hours per week per tutorial

and up to an additional 8 hours in some weeks for completing lab and project work, private study and revision.

Unit Relationships


Fundamental mathematics

Chief Examiner

Campus Lecturer

Academic Overview

Learning Outcomes

On completion of this unit students will have a knowledge and understanding of:
  • the applications of intelligent software systems;
  • the principles and theoretical underpinning of intelligent software systems;
  • the models and approaches to building intelligent software systems;
  • the advantages and limitations of intelligent models and approaches for solving a wide range of practical problems;
  • different software toolkits and development environments;
  • current research trends in the field.

Unit Schedule

Week Activities Assessment
0   No formal assessment or activities are undertaken in week 0
1 Introduction to Intelligent Systems and Neural Networks  
2 Neuron Learning and Perceptrons  
3 Multilayered Networks  
4 Supervised Learning - Backpropagation Learning Rule  
5 Classification and Prediction with Case Studies  
6 Unsupervised Learning - Clustering with Self-Organisation  
7 Unsupervised Learning with Adaptive Resonance Theory Assignment proposal due
8 Data Mining and Knowledge Discovery  
9 Other Intelligent Techniques  
10 Fuzzy Logic  
11 Business Intelligence Modelling - Decision Analysis under Uncertainty  
12 Decision Trees, Decision Making Using Sample Information; Revision and Exam Preparation Assignment due 30 May 2013
  SWOT VAC No formal assessment is undertaken in SWOT VAC
  Examination period LINK to Assessment Policy: http://policy.monash.edu.au/policy-bank/

*Unit Schedule details will be maintained and communicated to you via your learning system.

Assessment Summary

Examination (3 hours): 70%; In-semester assessment: 30%

Assessment Task Value Due Date
Solving A Neural Network Problem 30% 30 May 2013
Examination 1 70% To be advised

Teaching Approach

Lecture and tutorials or problem classes
This teaching and learning approach helps students to initially encounter information at lectures, discuss and explore the information during tutorials, and practice in a hands-on lab environment.

Assessment Requirements

Assessment Policy

Faculty Policy - Unit Assessment Hurdles (http://www.infotech.monash.edu.au/resources/staff/edgov/policies/assessment-examinations/unit-assessment-hurdles.html)

Academic Integrity - Please see the Demystifying Citing and Referencing tutorial at http://lib.monash.edu/tutorials/citing/

Assessment Tasks


  • Assessment task 1
    Solving A Neural Network Problem
    In this assignment, you will be applying what you have learnt about neural networks and the backpropagation learning algorithm to a forecasting, prediction or classification problem of your choice. You are required to write up your findings in the form of a short (4-6 pages) conference-type paper. When you have identified your problem, you need to write a one-page proposal which outlines your problem, where you will get your data set, and the methodology you will use. This needs to be handed out to your tutor for approval during your tutorial in Week 7.
    Criteria for assessment:

    The assessment will be based on both contents and presentation. You must get permission from your tutor for the problem you choose to do. You are expected to train your network and perform some sort of analysis of the results. The more analysis you do, the more insight you will gain into the problem and the technique (and the more marks you will receive).

    Due date:
    30 May 2013


  • Examination 1
    3 hours
    Type (open/closed book):
    Closed book
    Electronic devices allowed in the exam:
    Non-programmable calculators

Learning resources

Reading list

Recommended reading will be provided on the unit Moodle site.

Monash Library Unit Reading List

Feedback to you

Types of feedback you can expect to receive in this unit are:
  • Informal feedback on progress in labs/tutes
  • Graded assignments with comments
  • Solutions to tutes, labs and assignments

Extensions and penalties

Returning assignments

Assignment submission

It is a University requirement (http://www.policy.monash.edu/policy-bank/academic/education/conduct/plagiarism-procedures.html) for students to submit an assignment coversheet for each assessment item. Faculty Assignment coversheets can be found at http://www.infotech.monash.edu.au/resources/student/forms/. Please check with your Lecturer on the submission method for your assignment coversheet (e.g. attach a file to the online assignment submission, hand-in a hard copy, or use an online quiz).

Online submission

If Electronic Submission has been approved for your unit, please submit your work via the Moodle site for this unit, which you can access via links in the my.monash portal.

Other Information


Graduate Attributes Policy

Student services

Monash University Library

Disability Liaison Unit

Students who have a disability or medical condition are welcome to contact the Disability Liaison Unit to discuss academic support services. Disability Liaison Officers (DLOs) visit all Victorian campuses on a regular basis.

Your feedback to Us

Previous Student Evaluations of this Unit

In its first offering (2012) at the SEU-Monash Joint Graduate School in Suzhou, this unit has achieved a student evaluation score of 4.73 (out of 5) for the quality of the unit. Student feedback has shown that this unit is well structured and no changes are required for this semester. In particular, students are happy with the encouragement and helpful feedback they received from the lecturer for their active participation in this unit.

If you wish to view how previous students rated this unit, please go to

[an error occurred while processing this directive]