Course Title: Evolutionary Computing

Part A: Course Overview

Course Title: Evolutionary Computing

Credit Points: 12.00

Terms

Course Code

Campus

Career

School

Learning Mode

Teaching Period(s)

COSC1207

City Campus

Undergraduate

140H Computer Science & Information Technology

Face-to-Face

Sem 2 2006,
Sem 2 2007,
Sem 2 2008,
Sem 2 2009,
Sem 2 2010,
Sem 2 2011,
Sem 2 2012

COSC1207

City Campus

Undergraduate

171H School of Science

Face-to-Face

Sem 1 2019

COSC2033

City Campus

Postgraduate

140H Computer Science & Information Technology

Face-to-Face

Sem 2 2006,
Sem 2 2007,
Sem 2 2008,
Sem 2 2009,
Sem 2 2010,
Sem 2 2011,
Sem 2 2012

COSC2033

City Campus

Postgraduate

171H School of Science

Face-to-Face

Sem 1 2019

Course Coordinator: Dr Xiaodong Li

Course Coordinator Phone: +61 3 9925 9585

Course Coordinator Email: xiaodong.li@rmit.edu.au

Course Coordinator Location: 14.8.14B

Course Coordinator Availability: by appointment


Pre-requisite Courses and Assumed Knowledge and Capabilities

Enforced Prerequisites:

COSC1295 Advanced Programming OR

COSC1073 Programming 1 OR

COSC1283 Programming Techniques OR

COSC1076 Advanced Programming Techniques

It would be worthwhile if you have completed COSC1125 Artificial Intelligence, or you are studying it concurrently.

 


Course Description

Evolutionary computation is concerned with the use of simulated biological evolution to solve problems for which it can be difficult to write the programs using traditional methods. This course examines different models of evolutionary computation and the kinds of problems to which they can be applied.

 

Please note that if you take this course for a bachelor honours program, your overall mark in this course will be one of the course marks that will be used to calculate the weighted average mark (WAM) that will determine your award level. This applies to students who commence enrolment in a bachelor honours program from 1 January 2016 onwards. See the WAM information web page for more information.(http://www1.rmit.edu.au/browse;ID=eyj5c0mo77631)


Objectives/Learning Outcomes/Capability Development

 


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

  1. Demonstrate an understanding of the basic principles and techniques of genetic algorithms, genetic programming and swarm intelligence;
  2. Demonstrate an understanding of how to apply techniques of genetic algorithms, genetic programming and swarm intelligence to optimisation problems and problems that require machine learning;
  3. Compare different approaches to solve problems;
  4. Read and comprehend research papers in the area; and
  5. Lead discussion on current research issues.


Overview of Learning Activities

 

The learning activities included in this course are:

  • This course runs in a seminar mode where articles and book chapters are discussed and analysed.
  • You will be expected to read the prescribed book chapters or papers each week and come to the seminar class prepared to discuss the concepts and issues involved.
  • You will be expected to lead at least one seminar class. As well as the in-class activity, this will require posting focus questions to the newsgroup 4 days in advance.
  • In the laboratory classes at the beginning of the semester you will learn how to use the major software tools in the area. In the second part of the course you will use one of these tools in a major project, under the guidance of a lecturer. The laboratory hour will be used for discussing issues and problems relating to the project.

While a minimum attendance standard is not compulsory, non-attendance may seriously jeopardise the chances of success in this course. Clearly, non-attendance at an assessment will result in failure of that assessment. Where visa conditions apply, attendance is compulsory.

 

A total of 120 hours of study is expected during this course, comprising:

Teacher-directed hours (36 hours): The course has theoretical and practical components.  Learning activities relating to theory consist of reading the prescribed papers and participating in class discussions.  Learning activities relating to the practice involve understanding an existing evolutionary computing system, configuring it for a problem and carrying out experimental runs.  Some projects could involve considerable programming, while some other projects may require minimal programming.

There is a weekly two hour seminar (24 hours) and a laboratory class for one hour each week (12 hours).

Student-directed hours (84 hours): You are expected to be self-directed, studying independently outside class including reading the prescribed book chapters or papers each week and come to the seminar class prepared to discuss the concepts and issues involved.

 


Overview of Learning Resources

The course is supported by the Canvas learning management system which provides specific learning resources. See the RMIT Library Guide at http://rmit.libguides.com/compsci


Overview of Assessment

 

The assessment for this course consists of written summaries of reading material, an evaluation of participation in class discussions, a review paper and a programming assignment.

 For standard assessment details, including deadlines, weightings, and hurdle requirements relating to Computer Science and IT courses see: http://www.rmit.edu.au/compsci/cgi

 Note: This course has no hurdle requirements. There is no exam.

The assessment for this course comprises: 

 

Assessment Tasks

 

Assessment Task 1:  Summaries of Weekly Readings

Weighting 10%

This assessment task supports CLO 1

Assessment Task 2: Participation and Leadership of Discussion

Weighting 10%

This assessment task supports CLOs 4 & 5

 

Assessment Task 3: Written Assignment

Weighting 5%

This assessment task supports CLOs 2 & 3

This early assessment will provide you with feedback on your progress to help you identify improvements necessary.

Assessment 4: Project Proposal

Weighting 20% 

This assessment supports CLOs 2 & 3

Assessment 5: Project Presentation and Report

Weighting 55% 

This assessment supports CLOs 1, 4 &