COMP6611C: Advanced Topics in Embedded AI Systems (Spring 2025)

Computer Science and Engineering, Hong Kong University of Science and Technology

How to run machine learning models on mobile or embedded devices? What are the unique challenges in embedded AI systems?

Instructor: Xiaomin Ouyang
Class Time: Tuesday 4:30pm - 5:50pm, Thursday 4:30pm - 5:50pm (Room 2304, Lift 17/18)
Email: xmouyang@cse.ust.hk (For course-related queries, please use the subject starting from [COMP6611C])
Office Hour: Friday 4:30pm - 5:30pm, Room 3562, Lift 27/28
Teaching Assistants: Miss Liyu Zhang (lzhangcx@connect.ust.hk) (For enrolled students: Recorded videos for absent classes can be requested by emailing the TA directly.)

Communication and Announcement: Canvas is the main platform for communication and announcement. For students auditing without official enrollment, please email me your name, student ID, and email address to access the course resources not available here and to stay updated with any course changes.

Course Description: This course will enable students to have an in-depth understanding of embedded AI algorithms and their implementation in real systems and applications. The major topics include 1) basics on machine learning; 2) data and system challenges in embedded AI 3) AI techniques and their implementation on cutting-edge platforms 4) real-world applications, such as smart health and smart buildings. The course structure will primarily consist of instructor presentations, student presentations, paper summaries, and a course project. Students will work on an individual or team project to build an end-to-end embedded AI system. Students will also read and discuss the latest publications in the areas of embedded AI, Internet of Things, mobile systems, and ubiquitous computing.

Course Objectives: After completion of this course, the students will have in-depth understanding of challenges in embedded AI systems, hands-on experience in implementing state-of-the-art embedded AI algorithms in real-world systems or applications, and critical thinking ability to tackle embedded AI problems.

Pre-requisite: Basic understanding of machine learning is required. Familiarity or experience with the fundamentals of embedded or mobile systems are preferred.

Grading Scheme:

• Class attendance & discussion: 20%
• Project: 60%
  • Proposal presentation (10%)
  • Midterm presentation (10%)
  • Final presentation (20%)
  • Final report (20%)
• Paper presentation: 10%
• Paper Reviews: 10% (5 papers)

Reference Materials:

• Conferences: Proceedings of MobiCom/MobiSys/SenSys/UbiComp/IPSN/IoTDI/NeurIPS/ICML/ICLR/CVPR/ACL

• Book: Siam, S.I., et al. (2024). Artificial Intelligence of Things: A Survey. ACM Transactions on Sensor Networks. website

Course Syllabus