News
ShieLD: Shielding Cross-zone Communication within Limited-resourced IoT Devices running Vulnerable Software Stack, an IEEE TDSC Publication
Authors: Anum Khurshid, Sileshi Demesie Yalew, Mudassar Aslam and Shahid Raza Date: 1 Feb 2022 DOI Bookmark: https://doi.org/10.1109/TDSC.2022.3147262 A new publication on TrustZone-M Technology is accepted in IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING and...
New Edge Server t.RECS revision
A new major revision of the Edge Server board “t.RECS” has arrived from manufacturing and our partners from Christmann Informationstechnik + Medien GmbH & Co. KG (CHR) are now working on testing all its features and adapting the software to the new revision. The...
A Survey of Domain-Specific Architectures for Reinforcement Learning, at IEEE Access publication
Authors: M. Rothmann and M. Porrmann Date: 26 January 2022 DOI Bookmark: 10.1109/ACCESS.2022.3146518 Supported by VEDLIoT, a new survey of domain-specific architectures for reinforcement learning is now available through IEEEXplore. Reinforcement learning algorithms...
VEDLIoT is closely collaborating with the Bielefeld-Paderborn Joint Artificial Intelligence Institute – JAII and it’s related projects
VEDLIoT is closely collaborating with the Bielefeld-Paderborn Joint Artificial Intelligence Institute - JAII and it's related projects. The goal of JAII is to lay the foundations for human-centered AI systems that act as competent partners and feature real-world...
Next-generation AIoT applications – VEDLIoT-Open Call is now active!
The Next-generation AIoT applications – VEDLIoT-Open Call is now active! The VEDLIoT-Open call for cascaded funding is foreseen to explore new opportunities by extending the application of the VEDLIoT platform to a more extensive set of new and relevant use cases. It...
GA took place F2F despite COVID traveling restrictions
VEDLIoT partners met last week, from Thursday to Friday, January 27th and 28th, for a project General Assembly organized both by the University of Gothenburg and Chalmers University of Technology. Four months have passed since the last face to face meeting and once...
Boosting Machine Learning with tailored accelerators: Custom Function Units in Renode, by Antmicro, at Google Open Source Blog
Check on Google Open Source Blog a republishing of the Boosting Machine Learning with tailored accelerators: Custom Function Units in Renode, by Antmicro. CFU integration in Renode is already used in practice in the VEDLIoT project. VEDLIoT will use Renode to develop...
VEDLIoT paper at DATE 2022
We are happy to announce the acceptance of the VEDLIoT paper submitted to the Design, Automation and Test in Europe Conference (DATE 2022). The paper, entitled "VEDLIoT: Very Efficient Deep Learning in IoT", will be presented at the conference as a full Multi-Partner...
Introducing Modular Runtime Flows to Kenning, by Antmicro
Antmicro developed a library aiming to simplify the workflow with machine learning applications on edge devices called Kenning. Based on a variety of practical edge AI use cases that we are working with on a daily basis, we have now expanded its functionality to...
Pedestrian detections
Veoneer is creating a data set for pedestrian detections, including varying poses and trajectories of the pedestrian as well as varying weather conditions. The data set will be utilised by the VEDLIoT project to demonstrate the benefits of distributed deep learning...