logo
ResearchBunny Logo
An optical neural network using less than 1 photon per multiplication

Engineering and Technology

An optical neural network using less than 1 photon per multiplication

T. Wang, S. Ma, et al.

Discover groundbreaking research by Tianyu Wang, Shi-Yuan Ma, Logan G. Wright, Tatsuhiro Onodera, Brian C. Richard, and Peter L. McMahon, as they unveil an optical neural network that achieves 99% accuracy in handwritten-digit classification with minimal optical energy. This study showcases the remarkable potential for optical neural networks to deliver high accuracy with extremely low photon usage.

00:00
00:00
Playback language: English
Abstract
This paper experimentally demonstrates an optical neural network achieving 99% accuracy on handwritten-digit classification using -3.1 detected photons per weight multiplication and -90% accuracy using -0.66 photons per weight multiplication. The sub-photon-per-multiplication is enabled by noise reduction from accumulating scalar multiplications in dot-product sums, applicable to various optical-neural-network architectures. This work highlights the potential of optical neural networks for accurate results with extremely low optical energies.
Publisher
Nature Communications
Published On
Oct 26, 2022
Authors
Tianyu Wang, Shi-Yuan Ma, Logan G. Wright, Tatsuhiro Onodera, Brian C. Richard, Peter L. McMahon
Tags
optical neural networks
handwritten-digit classification
sub-photon-multiplication
noise reduction
accuracy
optical energies

Related Publications

Explore these studies to deepen your understanding of the subject.

An optical neural chip for implementing complex-valued neural network
Engineering and Technology

An optical neural chip for implementing complex-valued neural network

H. Zhang, M. Gu, et al.

Identifying mental health status using deep neural network trained by visual metrics
Medicine and Health

Identifying mental health status using deep neural network trained by visual metrics

S. B. Shafiei, Z. Lone, et al.

Accelerating network layouts using graph neural networks
Computer Science

Accelerating network layouts using graph neural networks

C. Both, N. Dehmamy, et al.

Convolutional neural network-based classification of glaucoma using optic radiation tissue properties
Medicine and Health

Convolutional neural network-based classification of glaucoma using optic radiation tissue properties

J. Kruper, A. Richie-halford, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny