VEDLIoT: Very Efficient Deep Learning in IoT
Paper i proceeding, 2022
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.
Författare
Martin Kaiser
Universität Bielefeld
R. Griessl
Universität Bielefeld
Nils Kucza
Universität Bielefeld
C. Haumann
Universität Bielefeld
L. Tigges
Universität Bielefeld
K. Mika
Universität Bielefeld
Jens Hagemeyer
Universität Bielefeld
F. Porrmann
Universität Bielefeld
U. Ruckert
Universität Bielefeld
Micha Vor Dem Berge
Christmann Informationstechnik + Medien
Stefan Krupop
Christmann Informationstechnik + Medien
Mario Porrmann
Universität Osnabrück
M. Tassemeier
Universität Osnabrück
Pedro Petersen Moura Trancoso
Chalmers, Data- och informationsteknik, Datorteknik
F. Qararyah
Stavroula Zouzoula
Chalmers, Data- och informationsteknik, Datorteknik
A.C. Casimiro
Universidade de Lisboa
A. Bessani
Universidade de Lisboa
J. Cecilio
Universidade de Lisboa
S. Andersson
Veoneer
Oliver Brunnegård
Veoneer
O. Eriksson
Veoneer
R. Weiss
Siemens
F. McIerhofer
Siemens
Hans Salomonsson
EmbeDL AB
E. Malekzadeh
EmbeDL AB
D. Odman
EmbeDL AB
A. Khurshid
RISE Research Institutes of Sweden
Pascal Felber
Université de Neuchâtel
Marcelo Pasin
Université de Neuchâtel
Valerio Schiavoni
Université de Neuchâtel
J. Menetrey
Antmicro
K. Gugala
Antmicro
P. Zierhoffer
Antmicro
Eric Knauss
Göteborgs universitet
Hans Martin Heyn
Göteborgs universitet
Proceedings of the 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022
963-968
9783981926361 (ISBN)
2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022
Virtual, Online, Belgium,
Virtual, Online, Belgium,
Very Efficient Deep Learning in IOT (VEDLIoT)
Europeiska kommissionen (EU) (EC/H2020/957197), 2020-11-01 -- 2023-10-31.
Ämneskategorier
Inbäddad systemteknik
Datavetenskap (datalogi)
Datorsystem
DOI
10.23919/DATE54114.2022.9774653