- "Enabling Deep Intelligence on Embedded Systems"
- Seulki Lee
- UNIST, South Korea
As deep learning for resource-constrained systems become more popular, we see an increased number of intelligent embedded systems such as IoT devices, robots, autonomous vehicles, and the plethora of portable, wearable, and mobile devices that are feature-packed with a wide variety of machine learning tasks. However, the performance of DNNs (deep neural networks) running on an embedded system is significantly limited by the platform’s CPU, memory, and battery size; and their scope is usually limited to simplistic inference tasks only. This tutorial introduces on-device deep learning algorithms and supporting systems designs, which enable embedded systems to efficiently perform deep intelligent tasks, deep neural networks in particular, beyond their limited computing resources. We name such on-device deep intelligence on embedded systems as Embedded Deep Intelligence. Specifically, we propose resource-aware learning strategies devised to overcome the fundamental constraints of embedded systems. Once deployed in the field with the proposed resource-aware learning strategies, embedded systems are not only able to perform deep inference tasks on sensor data but also update and re-train their learning models at run-time without requiring any help from any external system. Such an on-device learning capability of Embedded Deep Intelligence makes an embedded intelligent system real-time, privacy-aware, secure, autonomous, untethered, responsive, and adaptive without concern for its limited resources.
Dr. Seulki Lee is an assistant professor at the Department of Computer Science and Engineering (CSE) and Artificial Intelligence Graduate School (AIGS) at UNIST (Ulsan National Institute of Science and Technology), where he leads EAI Lab (Embedded Artificial Intelligence Lab). He earned his Ph.D. and M.S degrees in Computer Science at the University of North Carolina at Chapel Hill (UNC). His research aims to make resource-constrained real-time and embedded sensing systems capable of learning, adapting, and evolving. He published many peer-reviewed papers at international conferences in the fields of embedded systems and AI, including ACM MobiSys, ACM SenSys, ACM IPSN, ACM UbiComp (IMWUT), IEEE RTAS, and IEEE DCOSS. He received the best paper award in ACM AIoTChallenge (2020) and the best presentation award in ACM UbiComp (2020). Since 2019, he has served as a Technical Program Committee and Reviewer of several international conferences and journals, including AAAI, ACM SenSys, ACM CSCW, ACM IMWUT, IEEE PerCOm, ACM/IEEE CHASE, IEEE TC, IEEE TMC, and IEEE TETC.