Unit Outline
School of Engineering
College of Sciences and Engineering
ENG335
Computational Intelligence
Semester 2, 2023
Michael Negnevitsky
CRICOS Provider Code: 00586B
 
Unit Coordinator
Michael Negnevitsky
Email: Michael.Negnevitsky@utas.edu.au
 
 
What is the Unit About?
Unit Description
The unit covers rule-based expert systems, fuzzy expert systems, frame-based expert systems, artificial neural networks, evolutionary computation, hybrid intelligent systems and knowledge engineering. The aim of this course is to acquaint students with intelligent systems and provide them with a working knowledge for building these systems.
Intended Learning Outcomes
As per the Assessment and Results Policy 1.3, your results will reflect your achievement against specified learning outcomes.
On completion of this unit, you will be able to:
1
Design intelligent systems using neural networks, fuzzy logic and genetic algorithms for solving practical problems.
2
Evaluate performance of intelligent systems in solving specific problems in engineering and science.
3
Communicate the results of intelligent system designs through writing professional reports.
Requisites
REQUISITE TYPE
REQUISITES
Pre-requisite
KME271 or KMA252
Alterations as a result of student feedback
Alternations are results of the students feedback.
 
 
Teaching arrangements
ATTENDANCE MODE
TEACHING TYPE
LEARNING ACTIVITY
CONTACT HOURS
FREQUENCY
On Campus
Lectorial
Two-hour Lectorial
2
Weekly
Computer Laboratory
Two-hour computer lab sessions
2
Weekly
Attendance/Engagement Expectations
If your unit is offered On campus, it is expected that you will attend all on-campus and onsite learning activities. This is to support your own learning and the development of a learning community within the unit. If you are unable to attend regularly, please discuss the situation with your course coordinator and/or our UConnect support team.

If your unit is offered Online, it is expected you will engage in all those activities as indicated in the Unit Outline, including any self-directed learning.

If you miss a learning activity for a legitimate reason (e.g., illness, carer responsibilities) teaching staff will attempt to provide alternative activities (e.g., make up readings) where it is possible.
 
This unit is a face-to-face unit. All students must attend all lab sessions.
 
 
How will I be Assessed?
For more detailed assessment information please see MyLO.
Assessment schedule
ASSESSMENT TASK #
ASSESSMENT TASK NAME
DATE DUE
WEIGHT
LINKS TO INTENDED LEARNING OUTCOMES
ASSESSMENT TASK 1:
Assignment 1
Week 3
15 %
LO1, LO2, LO3
ASSESSMENT TASK 2:
Assignment 2
Week 5
15 %
LO1, LO2, LO3
ASSESSMENT TASK 3:
Assignment 3
Week 9
15 %
LO1, LO2, LO3
ASSESSMENT TASK 4:
Assignment 4
Week 12
15 %
LO1, LO2, LO3
ASSESSMENT TASK 5:
Project based examination
Exam Period
40 %
LO1, LO2, LO3
Assessment details
Assessment Task 1: Assignment 1
TASK DESCRIPTION:
Develop a fuzzy expert system for customer profiling. The system is to be used by a financial services provider for direct marketing. To make direct marketing more efficient, the system should target people who are most likely to buy certain financial products and services.
Submit a report detailing the fuzzy expert system design, performance and evaluation of your method.

TASK LENGTH:
Matlab code and 10 page report
DUE DATE:
Week 3
WEIGHT:
15 %
 
CRITERION #
CRITERION
MEASURES INTENDED LEARNING OUTCOME
1
design and apply rule based and fuzzy expert system for solving practical problem
incorporating acquired knowledge from consultation with field experts
LO1
2
contribute as a member of a team involved in development of intelligent systems
LO1
3
evaluate the design and performance of the developed rule based and fuzzy expert
system for solving specific complex problems in science and engineering
LO2
4
write a professional report to communicate the results of the rule based and fuzzy
expert system design
LO3
 
Assessment Task 2: Assignment 2
TASK DESCRIPTION:
Develop a three-layer back-propagation neural network and train it to classify Iris plants. Test the network using the test data and determine the recognition error. Create a single-layer competitive network to perform the same classification task. Test the network using the test data and determine its recognition error.
Submit a report detailing the neural network design, performance and evaluation of your method.

TASK LENGTH:
Matlab code and 10 page report
DUE DATE:
Week 5
WEIGHT:
15 %
 
CRITERION #
CRITERION
MEASURES INTENDED LEARNING OUTCOME
1
design and apply neural network system for solving practical problem incorporating
acquired knowledge from consultation with field experts
LO1
2
contribute as a member of a team involved in development of intelligent systems
LO1
3
evaluate the design and performance of the neural network system developed for
solving specific complex problems in science and engineering
LO2
4
write a professional report to communicate the results of the neural network system
design.
LO3
 
 
Assessment Task 3: Assignment 3
TASK DESCRIPTION:
Develop a genetic algorithm for solving the travelling salesman problem (TSP).
Submit a report detailing the genetic algorithm design, performance and evaluation of your method.

TASK LENGTH:
Matlab code and 10 page report
DUE DATE:
Week 9
WEIGHT:
15 %
 
CRITERION #
CRITERION
MEASURES INTENDED LEARNING OUTCOME
1
design and apply genetic algorithms for solving practical problem incorporating
acquired knowledge from consultation with field experts
LO1
2
contribute as a member of a team involved in development of intelligent systems
LO1
3
evaluate the design and performance of genetic algorithms developed for solving
specific complex problems in science and engineering
LO2
4
apply knowledge related to intellectual property rights and personal data protection in
the course of development of intelligent systems
LO2
5
write a professional report to communicate the results of the genetic algorithm design
LO3
 
Assessment Task 4: Assignment 4
TASK DESCRIPTION:
Develop a self-organising neural network to identify potentially failing banks.
Submit a report detailing the self-organising neural network design, performance and evaluation of your method.

TASK LENGTH:
Matlab code and 10 page report
DUE DATE:
Week 12
WEIGHT:
15 %
 
CRITERION #
CRITERION
MEASURES INTENDED LEARNING OUTCOME
1
design and apply neural network system for solving practical problem incorporating
acquired knowledge from consultation with field experts
LO1
2
contribute as a member of a team involved in development of intelligent systems
LO1
3
evaluate the design and performance of neural network systems developed for
solving specific complex problems in science and engineering
LO2
4
apply knowledge related to intellectual property rights and personal data protection in
the course of development of intelligent systems
LO2
5
write a professional report to communicate the results of neural network system
design
LO3
 
Assessment Task 5: Project based examination
TASK DESCRIPTION:
Development of an intelligent system for solving a real-world problem
The project-based exam will assess students on knowledge and skills developed throughout the unit in identifying a problem suitable for an intelligent system application,
designing a suitable intelligent system and evaluating and reporting the outcomes.

TASK LENGTH:
Matlab code and 10 page report
DUE DATE:
Exam Period
WEIGHT:
40 %
 
CRITERION #
CRITERION
MEASURES INTENDED LEARNING OUTCOME
1
Identify a real-world problem suitable for an intelligent system application and
determine the problem characteristics, specify the project objectives and determine
required resources for developing the system.
LO1
2
Select an appropriate tool and develop an intelligent system to solve the problem.
LO1
3
Evaluate the performance of the designed system.
LO2
4
Write a professional report communicating the results of the intelligent system design.
LO3
 
 
 
 
How your final result is determined
To pass this unit, you need to demonstrate your attainment of each of the Intended Learning Outcomes, achieve a final unit grade of 50% or greater, and pass any hurdle tasks.
 
Submission of assignments
Where practicable, assignments should be submitted to an assignment submission folder in MYLO. You must submit assignments by the due date or receive a penalty (unless an extension of time has been approved by the Unit Coordinator). Students submitting any assignment in hard copy, or because of a practicum finalisation, must attach a student cover sheet and signed declaration for the submission to be accepted for marking.
 
Requests for extensions
If you are unable to submit an assessment task by the due date, you should apply for an extension.
A request for an extension should first be discussed with your Unit Coordinator or teaching support team where possible. A request for an extension must be submitted by the assessment due date, except where you can provide evidence it was not possible to do so. Typically, an application for an extension will be supported by documentary evidence: however, where it is not possible for you to provide evidence please contact your Unit Coordinator.
The Unit Coordinator must notify you of the outcome of an extension request within 3 working days of receiving the request.
Late Penalties
Assignments submitted after the deadline will receive a late penalty of 5% of the original available mark for each calendar day (or part day) that the assignment is late. Late submissions will not be accepted more than 10 calendar days after the due date, or after assignments have been returned to other students on a scheduled date, whichever occurs first. Further information on Late Penalties can be found on the Assessments and Results Procedure.
 
Review of results and appeals
You are entitled to ask for a review of the marking and grading of your assessment task if there is an irregularity in the marking standards or an error in the process for determining the outcome of an assessment. Details on how to request a review of a mark for an assignment are outlined in the Review and Appeal of Academic Decisions Procedure.