Moving Deep Learning to the Edge

被引:49
|
作者
Vestias, Mario P. [1 ]
Duarte, Rui Policarpo [2 ]
de Sousa, Jose T. [2 ]
Neto, Horacio C. [2 ]
机构
[1] Inst Politecn Lisboa, Inst Super Engn Lisboa, Inst Engn Sistemas & Comp Invest & Desenvolviment, P-1959007 Lisbon, Portugal
[2] Univ Lisbon, Inst Super Tecn, Inst Engn Sistemas & Comp Invest & Desenvolviment, P-1049001 Lisbon, Portugal
关键词
artificial intelligence; deep learning; deep neural network; edge computing; NEURAL-NETWORKS; CLOUD; CLASSIFICATION; RECOGNITION; ACCELERATOR; INTERNET; FLOW; CNN; GO;
D O I
10.3390/a13050125
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning is now present in a wide range of services and applications, replacing and complementing other machine learning algorithms. Performing training and inference of deep neural networks using the cloud computing model is not viable for applications where low latency is required. Furthermore, the rapid proliferation of the Internet of Things will generate a large volume of data to be processed, which will soon overload the capacity of cloud servers. One solution is to process the data at the edge devices themselves, in order to alleviate cloud server workloads and improve latency. However, edge devices are less powerful than cloud servers, and many are subject to energy constraints. Hence, new resource and energy-oriented deep learning models are required, as well as new computing platforms. This paper reviews the main research directions for edge computing deep learning algorithms.
引用
收藏
页数:33
相关论文
共 50 条
  • [21] Neuron Manifold Distillation for Edge Deep Learning
    Tao, Zeyi
    Xia, Qi
    Li, Qun
    2021 IEEE/ACM 29TH INTERNATIONAL SYMPOSIUM ON QUALITY OF SERVICE (IWQOS), 2021,
  • [22] Autonomous Navigation in Vineyards with Deep Learning at the Edge
    Aghi, Diego
    Mazzia, Vittorio
    Chiaberge, Marcello
    ADVANCES IN SERVICE AND INDUSTRIAL ROBOTICS, RAAD 2020, 2020, 84 : 479 - 486
  • [23] Deep learning for potential field edge detection
    Zhang ZhiHou
    Yao Yu
    Shi ZeYu
    Wang Hu
    Qiao ZhongKun
    Wang ShengRen
    Qin LiMao
    Du ShiHui
    Luo Feng
    Liu WeiXin
    CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION, 2022, 65 (05): : 1785 - 1801
  • [24] When Deep Learning Meets Edge Computing
    Huang, Yutao
    Ma, Xiaoqiang
    Fan, Xiaoyi
    Liu, Jiangchuan
    Gong, Wei
    2017 IEEE 25TH INTERNATIONAL CONFERENCE ON NETWORK PROTOCOLS (ICNP), 2017,
  • [25] Learning deep edge prior for image denoising
    Fang, Yingying
    Zeng, Tieyong
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2020, 200
  • [26] EDGE: Explaining Deep Reinforcement Learning Policies
    Guo, Wenbo
    Wu, Xian
    Khan, Usmann
    Xing, Xinyu
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [27] Deep Reinforcement Learning Edge Workload Orchestrator for Vehicular Edge Computing
    Silva, Eliana Neuza
    da Silva, Fernando Mira
    2023 IEEE 9TH INTERNATIONAL CONFERENCE ON NETWORK SOFTWARIZATION, NETSOFT, 2023, : 44 - 52
  • [28] When Deep Learning Meets the Edge: Auto-Masking Deep Neural Networks for Efficient Machine Learning on Edge Devices
    Lin, Ning
    Lu, Hang
    Hu, Xing
    Gao, Jingliang
    Zhang, Mingzhe
    Li, Xiaowei
    2019 IEEE 37TH INTERNATIONAL CONFERENCE ON COMPUTER DESIGN (ICCD 2019), 2019, : 506 - 514
  • [29] Deep anomaly detection in expressway based on edge computing and deep learning
    Wang, Juan
    Wang, Meng
    Liu, Qingling
    Yin, Guanxiang
    Zhang, Yuejin
    JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2022, 13 (03) : 1293 - 1305
  • [30] Deep anomaly detection in expressway based on edge computing and deep learning
    Juan Wang
    Meng Wang
    Qingling Liu
    Guanxiang Yin
    Yuejin Zhang
    Journal of Ambient Intelligence and Humanized Computing, 2022, 13 : 1293 - 1305