MetaTinyML: End-to-End Metareasoning Framework for TinyML Platforms
IEEE Embedded Systems Letters · 2024-12 · 16 (4) · 393-396
DOI: 10.1109/les.2024.3446948 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Embedded Systems Letters, 2024-12. Verfasst von Mozhgan Navardi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 19 Literaturangaben. Gefördert von: Laboratory of Physical Sciences.
Abstract (Originalsprache)
Efficiently deploying deep neural networks on resource-limited embedded systems is crucial to meet real-time and power consumption requirements. Utilizing metareasoning as a higher-level controller along with tiny machine learning (TinyML) can enhance energy efficiency and reduce latency on such systems by overseeing available resources. This study introduces MetaTinyML, a comprehensive metareasoning framework for self-guided navigation on TinyML platforms. The framework adapts its decision-making process by factoring in environmental changes to select the most suitable algorithms for the current scenario. Implementation of MetaTinyML on an NVIDIA Jetson Nano 4-GB system integrated with a Jetbot ground vehicle demonstrated up to 50% power consumption enhancement. View a video demonstration of the MetaTinyML framework at: Video.
Förderung
- Laboratory of Physical Sciences
Zitieren
APA
Navardi, M., Humes, E., & Mohsenin, T. (2024). MetaTinyML: End-to-End Metareasoning Framework for TinyML Platforms. IEEE Embedded Systems Letters, 16(4), 393-396. https://doi.org/10.1109/les.2024.3446948
Vancouver
Navardi M, Humes E, Mohsenin T. MetaTinyML: End-to-End Metareasoning Framework for TinyML Platforms. IEEE Embedded Systems Letters. 2024;16(4):393-396. doi:10.1109/les.2024.3446948
BibTeX
@article{Navardi2024,
author = {Navardi, Mozhgan and Humes, Edward and Mohsenin, Tinoosh},
title = {MetaTinyML: End-to-End Metareasoning Framework for TinyML Platforms},
journal = {IEEE Embedded Systems Letters},
year = {2024},
volume = {16},
number = {4},
pages = {393--396},
doi = {10.1109/les.2024.3446948}
}
EUVIMED