43024 Introduction to Computational Intelligence
Warning: The information on this page is indicative. The subject outline for a
particular session, location and mode of offering is the authoritative source
of all information about the subject for that offering. Required texts, recommended texts and references in particular are likely to change. Students will be provided with a subject outline once they enrol in the subject.
Subject handbook information prior to 2024 is available in the Archives.
Credit points: 6 cp
Result type: Grade and marks
Requisite(s): 41040 Introduction to Artificial Intelligence OR 42172 Introduction to Artificial Intelligence
Description
This subject focuses on the fundamental concepts and algorithms of computational intelligence (CI), including fuzzy logic, fuzzy control, neural networks and evolutionary computation. Students engage in a series of lectures, assignments and hands-on experiments to solve real-life problems. Computational techniques are introduced to demonstrate how problems can be simulated by mathematical models. Students learn how to tackle these issues by applying various CI algorithms to extract the knowledge from the model and evaluate the model performance and the extracted knowledge. By doing this, students are able to learn the theories and process data through the existing CI models. The students also leverage the knowledge to design, develop and validate the CI-based solutions for the problems and challenges in real world.
Subject learning objectives (SLOs)
Upon successful completion of this subject students should be able to:
| 1. | Explain the social implications of CI techniques. (B.1) |
|---|---|
| 2. | Implement selected CI algorithms and apply them to benchmark datasets. (D.1) |
| 3. | Read research papers and synthesize new understanding to solve specific CI problems in real-world. (C.1) |
| 4. | Communicate CI theories, model results and solutions logically, efficiently, and clearly. (E.1) |
Course intended learning outcomes (CILOs)
This subject also contributes specifically to the development of the following Course Intended Learning Outcomes (CILOs):
- Socially Responsible: FEIT graduates identify, engage, and influence stakeholders, and apply expert judgment establishing and managing constraints, conflicts and uncertainties within a hazards and risk framework to define system requirements and interactivity. (B.1)
- Design Oriented: FEIT graduates apply problem solving, design thinking and decision-making methodologies in new contexts or to novel problems, to explore, test, analyse and synthesise complex ideas, theories or concepts. (C.1)
- Technically Proficient: FEIT graduates apply theoretical, conceptual, software and physical tools and advanced discipline knowledge to research, evaluate and predict future performance of systems characterised by complexity. (D.1)
- Collaborative and Communicative: FEIT graduates work as an effective member or leader of diverse teams, communicating effectively and operating autonomously within cross-disciplinary and cross-cultural contexts in the workplace. (E.1)
Teaching and learning strategies
This subject will consist of 12 weekly 1 hr lecturers along with 1 hr hands-on practice. During the class, we will show how the algorithm evolves, how to use the algorithm, and practically experiment on benchmark data.
Students will work to solve real-life problems during hands-on practice classes. Students will apply the algorithms to the public datasets, which will require preparation to be undertaken before each class, and they will receive feedback and guidance through each of their hands-on sessions. At the end of semester, students will deliver a final project, which requires fuzzy system implementation and one video presentation to show the knowledge and skills for the given real-world problem.
Content (topics)
Topic 1: fuzzy theory
Topic 2: fuzzy systems and control
Topic 3: neural networks
Topic 4: evolutionary computation
Topic 5: fuzzy systems with machine learning capability
Assessment
Assessment task 1: Knowledge Quiz
| Intent: | To demonstrate an understanding of computational intelligent theory and operation |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 3 and 4 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): C.1 and E.1 |
| Type: | Quiz/test |
| Groupwork: | Individual |
| Weight: | 20% |
| Length: | Online quiz (2 marks per topic, and each topic has 2-4 single-/multiple- option questions) |
Assessment task 2: Lab Practice
| Intent: | To apply computational intelligence algorithms to public data to solve problems |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 1, 2, 3 and 4 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): B.1, C.1, D.1 and E.1 |
| Type: | Laboratory/practical |
| Groupwork: | Individual |
| Weight: | 35% |
| Length: | Submission:
|
Assessment task 3: Final Project
| Intent: | Design a fuzzy inference system to solve a given problem |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 1, 2, 3 and 4 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): B.1, C.1, D.1 and E.1 |
| Type: | Project |
| Groupwork: | Individual |
| Weight: | 45% |
| Length: | Submission:
|
Minimum requirements
In order to pass the subject, a student must achieve an overall mark of 50% or more.
Recommended texts
- C. T. Lin and C. S. George Lee, Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent System, Prentice-Hall, 1996.
- Andries P. Engelbrecht, Computational Intelligence: An Introduction
- Lofti A. Zadeh, “Fuzzy Sets,” Information and Control, Vol. 8, pp. 338-353, 1965.
- E. H. Mamdani and S. Assilian, “An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller,” Int’l J. Man-Machine Studies, Vol. 7, No. 1, pp. 1-13, 1975.
- Juang, Chia-Feng, and Chin-Teng Lin. "An online self-constructing neural fuzzy inference network and its applications." IEEE transactions on Fuzzy Systems 6.1 (1998): 12-32.
- Chen, Cheng-Hung, Chin-Teng Lin, and Cheng-Jian Lin. "A functional-link-based fuzzy neural network for temperature control." 2007 IEEE Symposium on Foundations of Computational Intelligence. IEEE, 2007.
- Juang, Chia-Feng, and Yu-Cheng Chang. "Evolutionary-group-based particle-swarm-optimized fuzzy controller with application to mobile-robot navigation in unknown environments." IEEE Transactions on Fuzzy Systems 19.2 (2011): 379-392.
- Lin, Yang-Yin, et al. "A mutually recurrent interval type-2 neural fuzzy system (MRIT2NFS) with self-evolving structure and parameters." IEEE Transactions on Fuzzy Systems 21.3 (2013): 492-509.