All-Optical Computation of an Arbitrary Linear Transform Using Diffractive Networks

Onur Kulce; Deniz Mengu; Yair Rivenson; Aydogan Ozcan

All-Optical Computation of an Arbitrary Linear Transform Using Diffractive Networks

Onur Kulce, Deniz Mengu, Yair Rivenson, Aydogan Ozcan

Research output: Contribution to journal › Conference article › peer-review

Abstract

We show that an arbitrary complex-valued linear transform can be performed all-optically using diffractive neural networks that are trained using deep learning.

Original language	English
Journal	Optics InfoBase Conference Papers
State	Published - 1 Jan 2022
Externally published	Yes
Event	Computational Optical Sensing and Imaging, COSI 2022 - Vancouver, Canada Duration: 11 Jul 2022 → 15 Jul 2022

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Mechanics of Materials

Cite this

@article{f95c23d3faae4c358b24b57aa9a6652d,

title = "All-Optical Computation of an Arbitrary Linear Transform Using Diffractive Networks",

abstract = "We show that an arbitrary complex-valued linear transform can be performed all-optically using diffractive neural networks that are trained using deep learning.",

author = "Onur Kulce and Deniz Mengu and Yair Rivenson and Aydogan Ozcan",

note = "Publisher Copyright: {\textcopyright} 2022 The Author(s); Computational Optical Sensing and Imaging, COSI 2022 ; Conference date: 11-07-2022 Through 15-07-2022",

year = "2022",

month = jan,

day = "1",

language = "English",

journal = "Optics InfoBase Conference Papers",

issn = "2162-2701",

}

TY - JOUR

T1 - All-Optical Computation of an Arbitrary Linear Transform Using Diffractive Networks

AU - Kulce, Onur

AU - Mengu, Deniz

AU - Rivenson, Yair

AU - Ozcan, Aydogan

PY - 2022/1/1

Y1 - 2022/1/1

N2 - We show that an arbitrary complex-valued linear transform can be performed all-optically using diffractive neural networks that are trained using deep learning.

AB - We show that an arbitrary complex-valued linear transform can be performed all-optically using diffractive neural networks that are trained using deep learning.

UR - https://www.scopus.com/pages/publications/85139101603

M3 - Conference article

AN - SCOPUS:85139101603

SN - 2162-2701

JO - Optics InfoBase Conference Papers

JF - Optics InfoBase Conference Papers

T2 - Computational Optical Sensing and Imaging, COSI 2022

Y2 - 11 July 2022 through 15 July 2022

ER -

All-Optical Computation of an Arbitrary Linear Transform Using Diffractive Networks

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this