King's College London

Research portal

Toward an Intelligent Edge: Wireless Communication Meets Machine Learning

Research output: Contribution to journalArticle

Standard

Toward an Intelligent Edge : Wireless Communication Meets Machine Learning. / Zhu, Guangxu; Liu, Dongzhu; Du, Yuqing; You, Changsheng; Zhang, Jun; Huang, Kaibin.

In: IEEE COMMUNICATIONS MAGAZINE, Vol. 58, No. 1, 8970161, 01.2020, p. 19-25.

Research output: Contribution to journalArticle

Harvard

Zhu, G, Liu, D, Du, Y, You, C, Zhang, J & Huang, K 2020, 'Toward an Intelligent Edge: Wireless Communication Meets Machine Learning', IEEE COMMUNICATIONS MAGAZINE, vol. 58, no. 1, 8970161, pp. 19-25. https://doi.org/10.1109/MCOM.001.1900103

APA

Zhu, G., Liu, D., Du, Y., You, C., Zhang, J., & Huang, K. (2020). Toward an Intelligent Edge: Wireless Communication Meets Machine Learning. IEEE COMMUNICATIONS MAGAZINE, 58(1), 19-25. [8970161]. https://doi.org/10.1109/MCOM.001.1900103

Vancouver

Zhu G, Liu D, Du Y, You C, Zhang J, Huang K. Toward an Intelligent Edge: Wireless Communication Meets Machine Learning. IEEE COMMUNICATIONS MAGAZINE. 2020 Jan;58(1):19-25. 8970161. https://doi.org/10.1109/MCOM.001.1900103

Author

Zhu, Guangxu ; Liu, Dongzhu ; Du, Yuqing ; You, Changsheng ; Zhang, Jun ; Huang, Kaibin. / Toward an Intelligent Edge : Wireless Communication Meets Machine Learning. In: IEEE COMMUNICATIONS MAGAZINE. 2020 ; Vol. 58, No. 1. pp. 19-25.

Bibtex Download

@article{f584378114d440a3b4fbc3b403fe62ea,
title = "Toward an Intelligent Edge: Wireless Communication Meets Machine Learning",
abstract = "The recent revival of AI is revolutionizing almost every branch of science and technology. Given the ubiquitous smart mobile gadgets and IoT devices, it is expected that a majority of intelligent applications will be deployed at the edge of wireless networks. This trend has generated strong interest in realizing an {"}intelligent edge{"} to support AI-enabled applications at various edge devices. Accordingly, a new research area, called edge learning, has emerged, which crosses and revolutionizes two disciplines: wireless communication and machine learning. A major theme in edge learning is to overcome the limited computing power, as well as limited data, at each edge device. This is accomplished by leveraging the mobile edge computing platform and exploiting the massive data distributed over a large number of edge devices. In such systems, learning from distributed data and communicating between the edge server and devices are two critical and coupled aspects, and their fusion poses many new research challenges. This article advocates a new set of design guidelines for wireless communication in edge learning, collectively called learning- driven communication. Illustrative examples are provided to demonstrate the effectiveness of these design guidelines. Unique research opportunities are identified.",
author = "Guangxu Zhu and Dongzhu Liu and Yuqing Du and Changsheng You and Jun Zhang and Kaibin Huang",
year = "2020",
month = "1",
doi = "10.1109/MCOM.001.1900103",
language = "English",
volume = "58",
pages = "19--25",
journal = "IEEE COMMUNICATIONS MAGAZINE",
issn = "0163-6804",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Toward an Intelligent Edge

T2 - Wireless Communication Meets Machine Learning

AU - Zhu, Guangxu

AU - Liu, Dongzhu

AU - Du, Yuqing

AU - You, Changsheng

AU - Zhang, Jun

AU - Huang, Kaibin

PY - 2020/1

Y1 - 2020/1

N2 - The recent revival of AI is revolutionizing almost every branch of science and technology. Given the ubiquitous smart mobile gadgets and IoT devices, it is expected that a majority of intelligent applications will be deployed at the edge of wireless networks. This trend has generated strong interest in realizing an "intelligent edge" to support AI-enabled applications at various edge devices. Accordingly, a new research area, called edge learning, has emerged, which crosses and revolutionizes two disciplines: wireless communication and machine learning. A major theme in edge learning is to overcome the limited computing power, as well as limited data, at each edge device. This is accomplished by leveraging the mobile edge computing platform and exploiting the massive data distributed over a large number of edge devices. In such systems, learning from distributed data and communicating between the edge server and devices are two critical and coupled aspects, and their fusion poses many new research challenges. This article advocates a new set of design guidelines for wireless communication in edge learning, collectively called learning- driven communication. Illustrative examples are provided to demonstrate the effectiveness of these design guidelines. Unique research opportunities are identified.

AB - The recent revival of AI is revolutionizing almost every branch of science and technology. Given the ubiquitous smart mobile gadgets and IoT devices, it is expected that a majority of intelligent applications will be deployed at the edge of wireless networks. This trend has generated strong interest in realizing an "intelligent edge" to support AI-enabled applications at various edge devices. Accordingly, a new research area, called edge learning, has emerged, which crosses and revolutionizes two disciplines: wireless communication and machine learning. A major theme in edge learning is to overcome the limited computing power, as well as limited data, at each edge device. This is accomplished by leveraging the mobile edge computing platform and exploiting the massive data distributed over a large number of edge devices. In such systems, learning from distributed data and communicating between the edge server and devices are two critical and coupled aspects, and their fusion poses many new research challenges. This article advocates a new set of design guidelines for wireless communication in edge learning, collectively called learning- driven communication. Illustrative examples are provided to demonstrate the effectiveness of these design guidelines. Unique research opportunities are identified.

UR - http://www.scopus.com/inward/record.url?scp=85078757648&partnerID=8YFLogxK

U2 - 10.1109/MCOM.001.1900103

DO - 10.1109/MCOM.001.1900103

M3 - Article

VL - 58

SP - 19

EP - 25

JO - IEEE COMMUNICATIONS MAGAZINE

JF - IEEE COMMUNICATIONS MAGAZINE

SN - 0163-6804

IS - 1

M1 - 8970161

ER -

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454