<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Publication:
Programming nonlinear propagation for efficient optical learning machines

Loading...
Thumbnail Image

Departments

School / College / Institute

Item type:Organizational Unit,

Program

KU-Authors

Organization Authors

Co-Authors

Oguz, Ilker

Hsieh, Jih-Liang

Dinc, Niyazi Ulas

Yildirim, Mustafa

Gigli, Carlo

Moser, Christophe

Psaltis, Demetri

Date

Language

Embargo Status

Journal Title

Journal ISSN

Volume Title

Alternative Title

Abstract

The ever-increasing demand for training and inferring with larger machine-learning models requires more efficient hardware solutions due to limitations such as power dissipation and scalability. Optics is a promising contender for providing lower power computation, since light propagation through a nonabsorbing medium is a lossless operation. However, to carry out useful and efficient computations with light, generating and controlling nonlinearity optically is a necessity that is still elusive. Multimode fibers (MMFs) have been shown that they can provide nonlinear effects with microwatts of average power while maintaining parallelism and low loss. We propose an optical neural network architecture that performs nonlinear optical computation by controlling the propagation of ultrashort pulses in MMF by wavefront shaping. With a surrogate model, optimal sets of parameters are found to program this optical computer for different tasks with minimal utilization of an electronic computer. We show a remarkable decrease of 97% in the number of model parameters, which leads to an overall 99% digital operation reduction compared to an equivalently performing digital neural network. We further demonstrate that a fully optical implementation can also be performed with competitive accuracies.

Source

Publisher

SPIE

Citation

item.page.haspartof

Source

Advanced Photonics

item.page.ispartofseries

item.page.edition

DOI

10.1117/1.AP.6.1.016002

item.page.datauri

item.page.link

Rights

Copyrights Note

Endorsement

Review

Supplemented By

Referenced By

Related Patent

Related Goal

Google Scholar
Scholar'da Ara ↗
Altmetric
Dimensions
PlumX Metrikleri
BIP! Indicators