Abstract
We pushed the optical energy consumption of optical neural networks to a new regime. Despite dominant quantum noise, we experimentally achieved accurate image classification using 0.008 photons/MAC, demonstrating deterministic machine-learning tasks with ultra-low-power stochastic systems.
© 2023 The Author(s)
PDF Article | Presentation VideoMore Like This
Tianyu Wang, Shi-Yuan Ma, Logan G. Wright, Tatsuhiro Onodera, Brian Richard, and Peter L. McMahon
FTh6C.2 Frontiers in Optics (FiO) 2021
Y. Peng, Y. Yuan, S. Cheung, T. Van Vaerenbergh, W. V. Sorin, G. Kurczveil, Aashu Jha, Z. Huang, M. Fiorentino, and R. G. Beausoleil
FW6E.3 Frontiers in Optics (FiO) 2023
Farshid Ashtiani, Mohamad Hossein Idjadi, Ting-Chen Hu, Stefano Grillanda, David Neilson, Mark Earnshaw, Mark Cappuzzo, Rose Kopf, Alaric Tate, and Andrea Blanco-Redondo
FW6E.2 Frontiers in Optics (FiO) 2023