42172 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 2024 is available in the Archives.
Credit points: 6 cp
Result type: Grade and marks
There are course requisites for this subject. See access conditions.
Anti-requisite(s): 41040 Introduction to Artificial Intelligence
Description
This subject introduces students to the basic concepts and ideas of Artificial Intelligence (AI) algorithms and provides opportunities for students to get hands-on experience in applying some of the AI techniques to solve small to medium size problems. The AI techniques cover six key areas: learning, natural language processing, computer vision, searching, knowledge representation, and inference and reasoning. Through a series of lectures, hands-on laboratory experiments, students are exposed to a wide range of AI techniques and develop good understanding of these techniques, and skills to apply these techniques using existing packages and libraries. Students are assessed through a knowledge test, a set of mini AI application examples that apply selected AI techniques to solve simple problems and a group project in which project group designs a working solution to an interesting real-world problem. Upon completion of this subject, students are able to exemplify AI applications and demonstrate their understanding of AI techniques and skills of applying some of these techniques in real world applications.
Subject learning objectives (SLOs)
Upon successful completion of this subject students should be able to:
| 1. | Explain key ideas of common AI techniques. (D.1) |
|---|---|
| 2. | Apply common AI algorithms to solve simple problems. (C.1) |
| 3. | Justify AI algorithm selection. (D.1) |
| 4. | Collaborate effectively on a project team. (E.1) |
| 5. | Exemplify AI applications. (D.1) |
| 6. | Reflect on the development of their knowledge and skills as an AI professional. (F.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 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)
- Reflective: FEIT graduates critically self-review their own and others' performance with a high level of responsibility to improve and practice competently for the benefit of professional practice and society. (F.1)
Teaching and learning strategies
This subject will be delivered through a series of lectures and laboratory/ tutorials. In each week, students will attend a lecture class (1.5 hours) and a lab or a tutorial class (1.5 hours). Lecture classes will unpack the weekly topics. Students are expected to have adequate off class preparation so that they can make best use of lecture classes to build sound AI knowledge base; The lab classes include demonstration of the weekly AI techniques and exercise of using the AI techniques. The lab classes provide opportunities for students to make sense of the conceptual knowledge and gain hands-on experience of applying these AI techniques. The tutorial classes include explanation of concepts with examples and exercises for students to gain better understanding of the techniques for knowledge presentation, and knowledge-based reasoning and inference.
Content (topics)
- Overview of AI
- Machine learning
- Natural language processing
- Computer vision
- Searching
- Knowledge representation and inference/reasoning
Assessment
Assessment task 1: Mini AI application examples
| Intent: | Assess students’ ability to apply selected AI techniques to solve simple problems. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 2, 3, 5 and 6 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): C.1, D.1 and F.1 |
| Type: | Project |
| Groupwork: | Individual |
| Weight: | 45% |
| Length: | The length of each report is between 8 -10 standard A4 pages (standard setting including margins, font size and line spacing). The working program is a link to the colab notebook. |
Assessment task 2: Group project plan and design
| Intent: | This assignment equips students with AI thinking and critical analysis of various phases in undertaking AI projects, including defining problem statement, assessing, selecting, and developing methodologies, architectures, processes and workflow, and evaluation criteria. The task trains students to search and integrate domain-specific knowledge, problems, data and resources with AI methods and processes to design desirable solutions. The proposal integrates cross-disciplinary thinking, knowledge, and skills for data-driven evidence-based design to solve an interesting practical problem. Through this task, students will also develop skills of critical thinking and analysis of appropriate state-of-the-art AI technologies to address challenging real-world problems. |
|---|---|
| Objective(s): | This assessment task addresses the following subject learning objectives (SLOs): 2, 3, 4, 5 and 6 This assessment task contributes to the development of the following Course Intended Learning Outcomes (CILOs): C.1, D.1, E.1 and F.1 |
| Type: | Project |
| Groupwork: | Group, group and individually assessed |
| Weight: | 35% |
| Length: | The maximum length of the group project proposal is 15 pages. The minimum length of the individual reflection report is 5 pages. |
Assessment task 3: Exam
| Intent: | Assess students’ understanding of the key concepts underlying AI techniques and typical AI algorithms. |
|---|---|
| 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: | 20% |
| Length: | 100 minutes |
Minimum requirements
In order to pass the subject, a student must achieve an overall mark of 50% or more.
Required texts
Stuart J. Russell and Peter Norvig, Artificial Intelligence -- A Modern Approach, 4th Edition, Pearson, 2021.
Textbook website: aima.cs.berkeley.edu