Information on this page, including unit offerings, is from the 2020 academic year.
Intelligent Systems (ICT319)
|Organisational Unit||Information Technology, Mathematics and Statistics|
|Availability||MURDOCH: S2-internal, S2-external
DUBAI-ISC: TJD-internal, TSD-internal
KAPLAN-SGP: TJA-internal, TSA-internal
|Teaching Timetables||Murdoch S2
|Description||Offers an introduction to the fundamental concepts and techniques of artificial intelligence focusing on expert systems to solve engineering problems, data mining, data analysis for industries and intelligent agents in computer games. Topics include: introduction to artificial intelligence and applications; introduction to game AI; rule based expert systems; neural computing; fuzzy logic; genetic algorithms, intelligent agents, state machines and methods of evaluating these technologies.|
|Unit Learning Outcomes||On successful completion of this unit you should be able to:
1. Demonstrate an understanding of basic intelligent systems concepts
2. Be able to explain the theory, operation and strengths and weaknesses of state machines, expert systems, fuzzy logic engines, neural networks, genetic algorithms data mining tools and intelligent agents
3. Be able to explain the strengths and weaknesses of state machines, expert systems, fuzzy logic engines, neural networks, genetic algorithms, data mining tools and intelligent agents
4. Be able to choose an appropriate intelligent technique to solve a given problem
5. Know how to use off-the-shelf intelligence tools, including expert system shells artificial neural network and other simulators for solving problems
6. Explain the importance of representation and search in problem solving
7. Understand the role of applied knowledge in problem solving
8. Be able to evaluate the capability of an intelligent system to solve a real problem
|Timetabled Learning Activities||Lectures: 1 x 2 hours per week (theory and practice); computer laboratories: 1 x 2 hours per week (1 hour supervised) (practice).
All offerings of this unit include the equivalent of 30 hours of structured learning.
|Unit Learning Experiences||The approach to learning in this unit is a combination of lectures to cover the theory and practice of artificial intelligence and practical laboratory sessions designed to provide hands-on experience. Students work on open-source software in computer labs and/or they may download the software to their personal machines and do the exercises at home. Online quizzes assess knowledge gained during the semester, from both lectures and practical classes.
Options for the project are many, depending on the student's interests and skill. Students are free to develop a project of their own choosing, using either off-the-shelf applications or their own code, or they may choose to complete a structured project which involves an agent programming exercise in a C-like language. A short proposal is used to assess these for feasibility early in the semester. Extra reading and video tutorials are provided on a rich Moodle website.
|Assessment||1. Project proposal (10%). Students are required to submit a short proposal outlining their project idea, to be examined for feasibility. Individual feedback will be provided by tutors to support student's choices, warn of any difficulties that might be encountered and suggest options.
2. Online quizzes. (20%) Two online quizzes will be open during Weeks 7 and 14, each assessing the theoretical and practical material covered to date. Corrective feedback is provided at the end of each quiz week.
2. Project submission (20%) Online submission of a project report and possibly code to assess practical skills. Individual feedback from tutors is provided via the unit website.
3. Final exam. (50%) A two-hour short answer exam assesses theoretical understanding.
|Prerequisites||ICT167 Principles of Computer Science OR ICT104 Principles of Computer Science.|
|Exclusions||ICT219 Intelligent Systems.|
|Appears in these Courses/Majors:
see individual structures for context
|Internet Access Requirements||Murdoch units normally include an online component comprising materials, discussions, lecture recordings and assessment activities. All students, regardless of their location or mode of study, need to have access to and be able to use computing devices with browsing capability and a connection to the Internet via Broadband (Cable, ADSL or Mobile) or Wireless. The Internet connection should be readily available and allow large amounts of data to be streamed or downloaded (approximately 100MB per lecture recording). Students also need to be able to enter into online discussions and submit assignments online.|