VEDLIoT: Very Efficient Deep Learning in IoT
Martin Kaiser, Rene Griessl, Nils Kucza, Carola Haumann, Lennart, Tigges, Kevin Mika, Jens Hagemeyer, Florian Porrmann, Ulrich R\"uckert, Micha, vor dem Berge, Stefan. Krupop, Mario Porrmann, Marco Tassemeier, Pedro, Trancoso, Fareed Quararyah, Stavroula Zouzoula
TL;DR
The VEDLIoT project develops energy-efficient deep learning solutions for distributed AIoT systems, emphasizing modular hardware, safety, security, and applicability across diverse IoT domains.
Contribution
It introduces a holistic, scalable approach combining hardware modularity and optimized algorithms for efficient deep learning in IoT environments.
Findings
Prototype hardware platform demonstrated adaptability across applications
Energy efficiency improvements in deep learning models
Successful deployment in smart home, automotive, and industrial 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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.