41040 Introduction to 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 2025 is available in the Archives.
Credit points: 6 cp
Subject level:
Undergraduate
Result type: Grade and marksRequisite(s): 48023 Programming Fundamentals OR 41039 Programming 1
Recommended studies:
33230 Mathematics 2; 37181 Discrete Mathematics; linear algebra, probability, statistics, discrete logic
Description
This subject helps students develop good understanding of concepts and fundamental algorithm ideas of Artificial Intelligence (AI) in some areas: learning, natural language processing, computer vision, searching, knowledge representation, inference and reasoning. Through a series of lectures and hands-on laboratory experiments designated for specific AI techniques in the targeted areas, students develop good understanding of these techniques, ability to make good judgement on model/algorithm selection for given tasks, and competence in applying these AI techniques in simple applications.
Subject learning objectives (SLOs)
Upon successful completion of this subject students should be able to:
| 1. | Explain key concepts and applications of AI techniques. (D.1) |
|---|---|
| 2. | Design solutions to implement AI techniques to solve simple real world problems. (C.1) |
| 3. | Communicate the application of AI techniques in collaboration with team members. (E.1) |
Course intended learning outcomes (CILOs)
This subject also contributes specifically to the development of the following Course Intended Learning Outcomes (CILOs):
- 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 be delivered through weekly lectures, hands-on laboratories/tutorials with aid of an online learning management system. During the lectures, the selected Al techniques will be explained and discussed. Students are required to read and/or view designated materials for each lecture.
Laboratory sessions will be run in the first part of semester in which students will practice the AI techniques in small groups to solve simple problems with help from lab facilitators. They will learn from the lab demo programs and develop ability of explaining simple applications of common AI techniques and ability of design AI solutions for simple real-world problems.
Tutorial sessions will be run in the second part of semester in which students will apply the common knowledge representation and inference/reasoning techniques through examples supported by a tutor.
Students’ ability of explaining and applying the common AI techniques in simple scenarios will be assessed in an open-book exam. Their ability of explaining selected simple AI applications will be assessed through a series of AI technique demos and their competence of design AI solutions for simple real-world applications will be assessed through a group AI project. Their communication and collaboration skills will be developed through communication and collaboration between group members, giving AI technique demos and AI project presentations.
Content (topics)
- Introduction of concepts and evolution of AI
- Machine learning
- Natural language processing
- Computer vision
- Searching
- Knowledge representation
- Inference and Reasoning
Assessment
Assessment task 1: AI technique demos
| Intent: | Assess students’ ability to articulate their understanding of applying artificial intelligence techniques to solve practical problems based on existing libraries. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 1 and 3 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): D.1 and E.1 |
| Type: | Presentation |
| Groupwork: | Individual |
| Weight: | 40% |
| Length: | Each short video is no longer than 3 minutes (penalty will apply for exceeding this limit) |
Assessment task 2: AI Project
| Intent: | Assess a student’s ability to work in a small group, collaboratively develop a showcase of applying some selected AI techniques to solve an interesting real-world problem and effectively present the outcomes of the project. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 2 and 3 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): C.1 and E.1 |
| Type: | Project |
| Groupwork: | Group, group and individually assessed |
| Weight: | 30% |
| Length: | No line limit to the solution program. No page limit for the evaluation report. The project presentation video is no longer than 10 minutes (penalty will apply for exceeding this limit). The length of individual reflection is 300-600 words. |
Assessment task 3: Final Exam
| Intent: | Assess students’ ability of explaining and applying key concepts and common AI techniques in simple scenarios. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 1 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): D.1 |
| Type: | Examination |
| Groupwork: | Individual |
| Weight: | 30% |
| Length: | 120 minutes |
Minimum requirements
To pass this subject students must achieve an overall mark of 50% or greater.
Required texts
Stuart J. Russell and Peter Norvig, Artificial Intelligence -- A Modern Approach, 4th Edition, Pearson, 2021.
Textbook website: aima.cs.berkeley.edu
References
Details see the subject reading lists