Delocalized photonic deep learning on the Internet's edge
Tuesday, March 7, 2023
11 a.m. – 11:45 a.m. ET
>>Register for this Zoom webinar.
Alexander Sludds, PhD Candidate
Electrical Engineering & Computer Science
Advanced machine learning models are currently impossible to run on edge devices such as smart sensors and unmanned aerial vehicles owing to constraints on power, processing, and memory. Sludds will introduce an approach to machine learning inference based on delocalized analog processing across networks. In this approach, named Netcast, cloud-based “smart transceivers” stream weight data to edge devices, enabling ultraefficient photonic inference.
Sludds and his colleagues have demonstrated image recognition at ultralow optical energy of 40 attojoules per multiply (less than 1 photon per multiply) at 98.8% (93%) classification accuracy. They reproduced this performance in a Boston-area field trial over 86 kilometers of deployed optical fiber, wavelength multiplexed over 3 terahertz of optical bandwidth. Netcast allows milliwatt-class edge devices with minimal memory and processing to compute at teraFLOPS rates reserved for high-power (more than 100 watts) cloud computers.
Attendees can join and participate in the series via Zoom.