VEDLIoT: Very Efficient Deep Learning in IoT
Abstract
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.
Keywords
Cite
@article{arxiv.2207.00675,
title = {VEDLIoT: Very Efficient Deep Learning in IoT},
author = {Martin Kaiser and Rene Griessl and Nils Kucza and Carola Haumann and Lennart Tigges and Kevin Mika and Jens Hagemeyer and Florian Porrmann and Ulrich Rückert and Micha vor dem Berge and Stefan. Krupop and Mario Porrmann and Marco Tassemeier and Pedro Trancoso and Fareed Quararyah and Stavroula Zouzoula and Antonio Casimiro and Alysson Bessani and Jose Cecilio and Stefan Andersson and Oliver Brunnegard and Olof Eriksson and Roland Weiss and Franz Meierhöfer and Hans Salomonsson and Elaheh Malekzadeh and Daniel Ödman and Anum Khurshid and Pascal Felber and Marcelo Pasin and Valerio Schiavoni and Jämes Ménétrey and Karol Gugula and Piotr Zierhoffer and Eric Knauss and Hans-Martin Heyn},
journal= {arXiv preprint arXiv:2207.00675},
year = {2022}
}
Comments
This publication incorporates results from the VEDLIoT project, which received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 957197