EWSN 2024, 21st International Conference on Embedded Wireless Systems and Networks, PhD School, 10 December 2024, St. Regis Abu Dhabi, Abu Dhabi, UAE
TinyML enables the execution of machine learning models on resource-constrained devices, offering benefits in privacy and energy consumption. However, current research often limits TinyML to single-device, single-task scenarios, hindering the potential for
collaborative edge computing. In this respect, we believe that systems where TinyML-enabled devices collaborate directly with one another remain largely unexplored, presenting significant opportunities for innovation in cooperative edge computing. This doctoral research investigates collaborative TinyML systems comprised of highly constrained devices (e.g., < 1000 KB RAM, < 2000 KB flash storage), with objectives such as: developing methods for intelligent computation offloading, creating a lightweight networking system for node communication, and investigating protocols for enhanced
interoperability.
Type:
Conference
City:
Abu Dhabi
Date:
2024-12-10
Department:
Communication systems
Eurecom Ref:
7999
Copyright:
© ACM, 2024. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in EWSN 2024, 21st International Conference on Embedded Wireless Systems and Networks, PhD School, 10 December 2024, St. Regis Abu Dhabi, Abu Dhabi, UAE
See also:
