Edge Intelligence

Paving the Last Mile of Artificial Intelligence With Edge Computing

Zhi Zhou, Xu Chen, En Li, Liekang Zeng, Ke Luo, Junshan Zhang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.

Original languageEnglish (US)
JournalProceedings of the IEEE
DOIs
StatePublished - Jan 1 2019

Fingerprint

Artificial intelligence
Mobile computing
Recommender systems
Computer systems
Internet
Internet of things
Deep learning

Keywords

  • Artificial intelligence
  • deep learning
  • edge computing
  • edge intelligence.

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Edge Intelligence : Paving the Last Mile of Artificial Intelligence With Edge Computing. / Zhou, Zhi; Chen, Xu; Li, En; Zeng, Liekang; Luo, Ke; Zhang, Junshan.

In: Proceedings of the IEEE, 01.01.2019.

Research output: Contribution to journalArticle

@article{51c53ab755da4af78d65fcdfeb04e60f,
title = "Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing",
abstract = "With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.",
keywords = "Artificial intelligence, deep learning, edge computing, edge intelligence.",
author = "Zhi Zhou and Xu Chen and En Li and Liekang Zeng and Ke Luo and Junshan Zhang",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/JPROC.2019.2918951",
language = "English (US)",
journal = "Proceedings of the IEEE",
issn = "0018-9219",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Edge Intelligence

T2 - Paving the Last Mile of Artificial Intelligence With Edge Computing

AU - Zhou, Zhi

AU - Chen, Xu

AU - Li, En

AU - Zeng, Liekang

AU - Luo, Ke

AU - Zhang, Junshan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.

AB - With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.

KW - Artificial intelligence

KW - deep learning

KW - edge computing

KW - edge intelligence.

UR - http://www.scopus.com/inward/record.url?scp=85067598102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067598102&partnerID=8YFLogxK

U2 - 10.1109/JPROC.2019.2918951

DO - 10.1109/JPROC.2019.2918951

M3 - Article

JO - Proceedings of the IEEE

JF - Proceedings of the IEEE

SN - 0018-9219

ER -