arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1908.00080cs.LGcs.CVcs.NIstat.ML
收藏

网络边缘的机器学习:综述

Machine Learning at the Network Edge: A Survey

Clarkson University(克拉克森大学);SRC, Inc.(SRC公司);University of the Punjab(旁遮普大学);Microsoft Research(微软研究院)

M. G. Sarwar Murshed, Christopher Murphy, Daqing Hou, Nazar Khan, Ganesh Ananthanarayanan, Faraz Hussain

摘要:

资源受限的物联网设备,如传感器和执行器,近年来已经变得无处不在。这导致了大量数据的实时生成,这是人工智能系统的一个有吸引力的目标。然而,在这样的终端设备上部署机器学习模型几乎是不可能的。典型的解决方案涉及将数据卸载到外部计算系统(如云服务器)进行进一步处理,但这会增加延迟,导致通信成本增加,并增加隐私问题。为了解决这个问题,已经努力将额外的计算设备放置在网络的边缘,即靠近生成数据的IoT设备。在这样的边缘计算设备上部署机器学习系统通过允许在接近数据源的地方执行计算来解决上述问题。本调查描述了在计算机网络边缘部署机器学习系统的主要研究工作,重点关注智能边缘系统成功应用中使用的操作方面,包括压缩技术,工具,框架和硬件。

英文摘要:

Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑