41041 Emerging Topics in Artificial 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 2021 is available in the Archives.
Credit points: 6 cp
Result type: Grade and marks
Requisite(s): 41040 Introduction to Artificial Intelligence
Recommended studies:
Some experience with an integrated development environment such as Anaconda with Python would be an advantage.
Description
This subject helps students develop good understanding of the concepts and related algorithms in emerging topics in Artificial Intelligence (AI). It is suitable for students who are enthusiastic about AI and keen to do research in AI areas. Most emerging AI topics and their applications will be discussed. Students have opportunities to explore their selected most favourite topics through literature reviews, group discussions and/or experimental investigation if applicable. Students need to demonstrate their good understanding of their chosen topics through, class engagement, a research report and an oral presentation.
Subject learning objectives (SLOs)
Upon successful completion of this subject students should be able to:
| 1. | Exemplify emerging AI topics |
|---|---|
| 2. | Explain key ideas of specific chosen emerging AI topics |
| 3. | Explore applications of emerging AI techniques |
| 4. | Communicate efficiently in both oral and written forms |
| 5. | Work in a team effectively |
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, interpret and analyse stakeholder needs and cultural perspectives, establish priorities and goals, and identify constraints, uncertainties and risks (social, ethical, cultural, legislative, environmental, economics etc.) to define the system requirements. (B.1)
- Design Oriented: FEIT graduates apply problem solving, design and decision-making methodologies to develop components, systems and processes to meet specified requirements. (C.1)
- Technically Proficient: FEIT graduates apply abstraction, mathematics and discipline fundamentals, software, tools and techniques to evaluate, implement and operate systems. (D.1)
- Collaborative and Communicative: FEIT graduates work as an effective member or leader of diverse teams, communicating effectively and operating within cross-disciplinary and cross-cultural contexts in the workplace. (E.1)
Teaching and learning strategies
This subject will have one 3 hrs face-to-face class each week for 12 weeks. In each class, the lecturer/guest lecturer will first give a brief introduction to a designated AI topic, then students will discuss this topic in small groups and present their results. The presentations will be assessed by the lecturer and other students through a pre-defined peer review process.
To demonstrate their good understanding of their chosen AI topics, students are required to explore in-depth the topics through literatures reviews and other learning activities and develop a research report, and give an oral presentation about their findings.
Content (topics)
Topics may include but not be limited to:
- Deep learning
- Computer Vision and Multimedia
- Reinforcement Learning
- Concept Drift-detection and adaptation
- Transfer learning/Fuzzy Transfer Learning
- Brain Computer Interface
- Recommender Systems
- Technology Intelligence
- Social robotics
- Data-driven decision support systems
Assessment
Assessment task 1: Class Engagement
| Intent: | To gain deep understanding about the issues in the selected topic areas and enhance oral communication skills. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 1, 2, 4 and 5 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: | Exercises |
| Groupwork: | Individual |
| Weight: | 20% |
Assessment task 2: Literature review and report
| Intent: | Learn how to clearly present the state-of-the-art development in chosen AI topic areas. |
|---|---|
| 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): B.1, C.1, D.1 and E.1 |
| Type: | Literature review |
| Groupwork: | Individual |
| Weight: | 50% |
Assessment task 3: Research Presentation
| Intent: | This task assesses a students's oral communication skills and ability to present arguments clearly and concisely to specialist and non-specialist audiences. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 2, 3 and 4 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): B.1 and E.1 |
| Type: | Presentation |
| Groupwork: | Individual |
| Weight: | 30% |
Minimum requirements
In order to pass the subject, a student must achieve an overall mark of 50% or more.
Recommended texts
1. Bishop, Christopher M., Pattern recognition and machine learning, New York: Springer, 2007, c2006.
2. Shalev-Shwartz, Shai, and Shai Ben-David. Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.References
1. UTS Harvard style 25 oct
2. Su, Xiaoyuan, and Taghi M. Khoshgoftaar. "A survey of collaborative filtering techniques." Advances in artificial intelligence 2009 (2009).
3. Burke, Robin. "Hybrid recommender systems: Survey and experiments." User modeling and user-adapted interaction12.4 (2002): 331-370.
4. Adomavicius, Gediminas, and Alexander Tuzhilin. "Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions." IEEE Transactions on Knowledge & Data Engineering 6 (2005): 734-749.
5. Shi, Yue, Martha Larson, and Alan Hanjalic. "Collaborative filtering beyond the user-item matrix: A survey of the state of the art and future challenges." ACM Computing Surveys (CSUR) 47.1 (2014): 3.
6. Gama, J., èliobait?, I., Bifet, A., Pechenizkiy, M. and Bouchachia, A., 2014. A survey on concept drift adaptation. ACM computing surveys (CSUR), 46(4), p.44. (A*journal paper, cited by 711)
7. Gomes, H.M., Barddal, J.P., Enembreck, F. and Bifet, A., 2017. A survey on ensemble learning for data stream classification. ACM Computing Surveys (CSUR), 50(2), p.23. (A*journal paper, cited by 44)
8. B. Krawczyk, L.L. Minku, J. Gama, J. Stefanowski, M. Wo?niak, Ensemble learning for data stream analysis: A survey, Information Fusion. 37 (2017) 132–156. (C journal paper, cited by 104)
9. G. Ditzler, M. Roveri, C. Alippi, R. Polikar, Learning in Nonstationary Environments: A Survey, IEEE Computational Intelligence Magazine.
10 (2015) 12–25. (C journal paper, cited by 159) 10. Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10), 1345-1359.
11. Shao L, Zhu F, Li X. Transfer learning for visual categorization: A survey [J]. IEEE transactions on neural networks and learning systems, 2015, 26(5): 1019-1034.
12. Patel V M, Gopalan R, Li R, et al. Visual domain adaptation: A survey of recent advances [J]. IEEE signal processing magazine, 2015, 32(3): 53-69.
13. Sun S, Shi H, Wu Y. A survey of multi-source domain adaptation [J]. Information Fusion, 2015, 24: 84-92.
14. C. A. Astudillo and B. J. Oommen, “Topology-oriented self-organizing maps: A survey,” Pattern Anal. Appl., vol. 17, no. 2, pp. 223–248, 2014.
15. B. Krawczyk, L. L. Minku, J. Gama, J. Stefanowski, and M. Wo?niak, “Ensemble learning for data stream analysis: A survey,” Inf. Fusion, vol. 37, pp. 132–156, 2017.
16. B. Silverman et al., “An Overview of Concept Drift Applications,” IEEE Trans. Fuzzy Syst., vol.
17, no. 2, pp. 1–29, 2016. 17. J. Gama, I. èliobait?, A. Bifet, M. Pechenizkiy, and A. Bouchachia, “A survey on concept drift adaptation,” ACM Comput. Surv., vol. 46, no. 4, pp. 1–37, 2014.
18. Losing V, Hammer B, Wersing H. Incremental on-line learning: A review and comparison of state of the art algorithms [J]. Neurocomputing, 2018, 275: 1261-1274.
19. H. L. Nguyen, Y. K. Woon, and W. K. Ng, “A survey on data stream clustering and classification,” Knowl. Inf. Syst., vol. 45, no. 3, pp. 535–569, 2015.
20. Lu, J., Wu, D., Mao, M., Wang, W., & Zhang, G. (2015), Recommender system application developments: A survey, Decision Support Systems, 74, 12-32.