EdgenAI: Distributed Inference with Local Edge Devices and Minimum Latency
TimeTuesday, December 7th6:00pm - 7:00pm PST
LocationLevel 2 - Lobby
Event Type
Networking Reception
Work-in-Progress Poster
Virtual Programs
Presented In-Person
DescriptionWe propose EdgenAI, a framework to decompose complex
deep neural networks over n available edge devices with minimal communication overhead and overall latency. Our framework creates small DNNs (SNNs) from an original DNN by partitioning its classes across the edge devices, while taking into account their available resources SDNNs perform inference in parallel and are additionally configured to generate a “Don’t Know” response when identifying an unassigned class. Our experiments show up to 17X speedup compared to a recent work, on devices with at most 100MB memory when distributing a variant of VGG-16 over 21 edge devices, without accuracy loss.