Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
Conferences > ACPC > 2021 > T4A > T4A.164

UONN: Energy-Efficient Optical Neural Network

Jiaxu Zhang, Yinyi Liu, Jun Feng, Shixi Chen, Tongyu Wu, Xiaowen Dong, and Jiang Xu

Not Accessible

Your library or personal account may give you access

Abstract

This work proposes a novel loop-based optical neural network UONN capable of large-scale vector-matrix multiplications. Results show that UONN can achieve up to 6000 X higher energy efficiency than existing MZI-based neural network.

© 2021 The Author(s)

PDF Article
Select as filters
Select Topics Cancel
Top
       
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.
Privacy | Terms of Use