Lightweight Deep Learning for Resource-Constrained Environments: A Survey
ACM Computing Surveys · 31.10.2024 · 56 (10) · 1-42
DOI: 10.1145/3657282 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 24.06.2024. Verfasst von Hou-I Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 275-mal zitiert (Crossref) und nennt 256 Literaturangaben. Gefördert von: National Science and Technology Council, Taiwan, National Key Fields Industry-University Cooperation and Skilled Personnel Training Act, Ministry of Education (MOE) and industry partners in Taiwan.
Abstract (Originalsprache)
Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model’s accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.
Förderung
- National Science and Technology Council, Taiwan
- National Key Fields Industry-University Cooperation and Skilled Personnel Training Act
- Ministry of Education (MOE) and industry partners in Taiwan
Zitieren
APA
Liu, H., Galindo, M., Xie, H., Wong, L., Shuai, H., Li, Y., & Cheng, W. (2024). Lightweight Deep Learning for Resource-Constrained Environments: A Survey. ACM Computing Surveys, 56(10), 1-42. https://doi.org/10.1145/3657282
Vancouver
Liu H, Galindo M, Xie H, Wong L, Shuai H, Li Y, et al. Lightweight Deep Learning for Resource-Constrained Environments: A Survey. ACM Computing Surveys. 2024;56(10):1-42. doi:10.1145/3657282
BibTeX
@article{Liu2024,
author = {Liu, Hou-I and Galindo, Marco and Xie, Hongxia and Wong, Lai-Kuan and Shuai, Hong-Han and Li, Yung-Hui and Cheng, Wen-Huang},
title = {Lightweight Deep Learning for Resource-Constrained Environments: A Survey},
journal = {ACM Computing Surveys},
year = {2024},
volume = {56},
number = {10},
pages = {1--42},
doi = {10.1145/3657282}
}
EUVIMED