TA1a.2

On the Design of Reconfigurable Edge Devices for RF Fingerprint Identification (RED-RFFI) for IoT Systems

Thomas Keller, Joseph R. Cavallaro, Rice University, United States
Session:
TA1a: Machine Learning Accelerators (invited) Lecture
Track:
Architectures and Implementation
Location:
Evergreen
Presentation Time:
Tue, 31 Oct, 08:40 - 09:05 PT (UTC -7)
Session Chair:
Joseph Cavallaro, Rice University
Presentation
Discussion
Resources
No resources available.
Session TA1a
TA1a.1: Ergodic Approximate Deep Learning Accelerators
Tim van Lijssel, Alexios Balatsoukas-Stimming, Eindhoven University of Technology, Netherlands
TA1a.2: On the Design of Reconfigurable Edge Devices for RF Fingerprint Identification (RED-RFFI) for IoT Systems
Thomas Keller, Joseph R. Cavallaro, Rice University, United States
TA1a.3: Dynamically Reconfigurable Perception using Dataflow Parameterization of Channel Attention
Yujunrong Ma, University of Maryland, United States; Kshitij Nikhal, University of Nebraska-Lincoln, United States; Jani Boutellier, University of Vaasa, Finland; Benjamin Riggan, University of Nebraska-Lincoln, United States; Shuvra Bhattacharyya, University of Maryland, United States
TA1a.4: Bringing Machine Learning to 6G: from TensorFlow to Over-the-Air with the Aerial Research Cloud
Chris Dick, Nvidia, United States
Contacts