Скачать с ютуб Alexander Sludds—Delocalized photonic deep learning on the Internet's edge в хорошем качестве

Alexander Sludds—Delocalized photonic deep learning on the Internet's edge

Alexander Sludds, a PhD candidate in the Electrical Engineering & Computer Science at MIT, gave the Nano Explorations talk on March 7, 2023. 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. ------------------------------------------------------ Nano Explorations is a virtual seminar series powered by MIT.nano that features presentations by MIT students and postdocs on their work in nanoscience, nanotechnology, and other advanced research fields. The series was launched as a way to keep our nano community connected during the COVID-19 pandemic. Presentations take place once a month and are open to any interested viewers. Read more about past and upcoming Nano Explorations at mitnano.mit.edu/nano-explorations.