Vedliot：物联网中非常有效的深度学习

论文标题

Vedliot：物联网中非常有效的深度学习

VEDLIoT: Very Efficient Deep Learning in IoT

论文作者

Kaiser, Martin, Griessl, Rene, Kucza, Nils, Haumann, Carola, Tigges, Lennart, Mika, Kevin, Hagemeyer, Jens, Porrmann, Florian, Rückert, Ulrich, dem Berge, Micha vor, Krupop, Stefan., Porrmann, Mario, Tassemeier, Marco, Trancoso, Pedro, Quararyah, Fareed, Zouzoula, Stavroula, Casimiro, Antonio, Bessani, Alysson, Cecilio, Jose, Andersson, Stefan, Brunnegard, Oliver, Eriksson, Olof, Weiss, Roland, Meierhöfer, Franz, Salomonsson, Hans, Malekzadeh, Elaheh, Ödman, Daniel, Khurshid, Anum, Felber, Pascal, Pasin, Marcelo, Schiavoni, Valerio, Ménétrey, Jämes, Gugula, Karol, Zierhoffer, Piotr, Knauss, Eric, Heyn, Hans-Martin

论文摘要

Vedliot项目针对分布式AIOT应用的节能深度学习的开发。整体方法用于优化算法，同时还应对安全和安全挑战。该方法基于模块化和可扩展的认知物联网硬件平台。使用模块化微功能技术使用户能够配置硬件以满足各种应用程序。 Vedliot为下一代物联网设备提供了完整的设计流，以协作解决跨分布式系统的复杂深度学习应用所需的。这些方法在各种用例上进行了测试，从智能家居到汽车和工业物联网设备。 Vedliot是一个H2020 EU项目，始于2020年11月。目前处于中级阶段，首先可获得。

The VEDLIoT project targets the development of energy-efficient Deep Learning for distributed AIoT applications. A holistic approach is used to optimize algorithms while also dealing with safety and security challenges. The approach is based on a modular and scalable cognitive IoT hardware platform. Using modular microserver technology enables the user to configure the hardware to satisfy a wide range of applications. VEDLIoT offers a complete design flow for Next-Generation IoT devices required for collaboratively solving complex Deep Learning applications across distributed systems. The methods are tested on various use-cases ranging from Smart Home to Automotive and Industrial IoT appliances. VEDLIoT is an H2020 EU project which started in November 2020. It is currently in an intermediate stage with the first results available.

下载PDF全文

下载文献需遵守相关版权规定

论文标题