1.
| understand the basics and general frameworks of the common AI approaches (e.g., search, machine learning, deep learning) for problem solving |
2.
| understand the workflow, the capabilities and the limitations of some state-of-the-art AI technologies, platforms and tools for solving data intensive problems with AI approaches |
3.
| identify potential AI-oriented tasks in a problem; design and implement AI pipelines properly in solving the corresponding tasks |
4.
| carry out AI experimentation with justifiable processes and evaluation; analyze and address potential issues arising from the experimentation |
Mapping from Course Learning Outcomes to Programme Learning Outcomes
| PLO a | PLO b | PLO c | PLO d | PLO e | PLO f | PLO g | PLO h | PLO i | PLO j |
CLO 1 | T | T | | | | T | | T | T | |
CLO 2 | T | T | | | | | | | T | T |
CLO 3 | | T | T | T | T | T | T | T | | T |
CLO 4 | | | T | T | T | | T | T | | T |
T - Teach, P - Practice
For BEng(CompSc) Programme Learning Outcomes, please refer to
here.
|
Syllabus |
Calendar Entry:
This course allows students to experience a complete AI experimentation and evaluation cycle with a hands-on project. The course comprises two main components: students first acquire the basic know-how of the state-of-the-art AI technologies, platforms and tools (e.g., TensorFlow, PyTorch, scikit-learn) via example-based modules in a self-paced learning mode. Students will then identify a creative or practical data-driven application and implement an AI-powered solution for the application as the course project.
|
Detailed Description:
Self-Paced Learning |
Mapped to CLOs
|
Introduction to AI methodologies and the experimentation cycle | 1, 2 |
Selected state-of-the-art AI platforms & tools | 1, 2 |
Project |
Mapped to CLOs
|
Problem Identification | 1, 2, 3 |
Implementation | 1, 2, 3, 4 |
Demonstration & Presentation | 1, 2, 3, 4 |
|
Assessment:
Continuous Assessment:
100%
|
Teaching Plan |
Please refer to the corresponding Moodle course.
|
Moodle Course(s) |
|