Improving the inference accuracy of diffractive optical neural networks using class-specific differential detection

Jingxi Li; Deniz Mengu; Yi Luo; Yair Rivenson; Aydogan Ozcan

doi:10.1364/CLEO_SI.2020.SM1E.3

Improving the inference accuracy of diffractive optical neural networks using class-specific differential detection

Jingxi Li
, Deniz Mengu
, Yi Luo
, Yair Rivenson
, Aydogan Ozcan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

We report all-optical object classification systems that are based on class-specific design of diffractive neural networks followed by a differential detection scheme. The blind inference accuracies achieved through this framework are significantly enhanced.

Original language	English
Title of host publication	CLEO
Subtitle of host publication	Science and Innovations, CLEO_SI 2020
Publisher	Optica Publishing Group (formerly OSA)
ISBN (Print)	9781943580767
DOIs	https://doi.org/10.1364/CLEO_SI.2020.SM1E.3
State	Published - 1 Jan 2020
Externally published	Yes
Event	CLEO: Science and Innovations, CLEO_SI 2020 - Washington, United States Duration: 10 May 2020 → 15 May 2020

Publication series

Name	Optics InfoBase Conference Papers
Volume	Part F183-CLEO-SI 2020
ISSN (Electronic)	2162-2701

Conference

Conference	CLEO: Science and Innovations, CLEO_SI 2020
Country/Territory	United States
City	Washington
Period	10/05/20 → 15/05/20

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Mechanics of Materials

Access to Document

10.1364/CLEO_SI.2020.SM1E.3

Cite this

Li, J., Mengu, D., Luo, Y., Rivenson, Y., & Ozcan, A. (2020). Improving the inference accuracy of diffractive optical neural networks using class-specific differential detection. In CLEO: Science and Innovations, CLEO_SI 2020 Article SM1E.3 (Optics InfoBase Conference Papers; Vol. Part F183-CLEO-SI 2020). Optica Publishing Group (formerly OSA). https://doi.org/10.1364/CLEO_SI.2020.SM1E.3

@inproceedings{e85d0c542ad543b0a60bff485d31b744,

title = "Improving the inference accuracy of diffractive optical neural networks using class-specific differential detection",

abstract = "We report all-optical object classification systems that are based on class-specific design of diffractive neural networks followed by a differential detection scheme. The blind inference accuracies achieved through this framework are significantly enhanced.",

author = "Jingxi Li and Deniz Mengu and Yi Luo and Yair Rivenson and Aydogan Ozcan",

note = "Publisher Copyright: {\textcopyright} OSA 2020 {\textcopyright} 2020 The Author(s); CLEO: Science and Innovations, CLEO\_SI 2020 ; Conference date: 10-05-2020 Through 15-05-2020",

year = "2020",

month = jan,

day = "1",

doi = "10.1364/CLEO\_SI.2020.SM1E.3",

language = "English",

isbn = "9781943580767",

series = "Optics InfoBase Conference Papers",

publisher = "Optica Publishing Group (formerly OSA)",

booktitle = "CLEO",

}

Li, J, Mengu, D, Luo, Y, Rivenson, Y & Ozcan, A 2020, Improving the inference accuracy of diffractive optical neural networks using class-specific differential detection. in CLEO: Science and Innovations, CLEO_SI 2020., SM1E.3, Optics InfoBase Conference Papers, vol. Part F183-CLEO-SI 2020, Optica Publishing Group (formerly OSA), CLEO: Science and Innovations, CLEO_SI 2020, Washington, United States, 10/05/20. https://doi.org/10.1364/CLEO_SI.2020.SM1E.3

Improving the inference accuracy of diffractive optical neural networks using class-specific differential detection. / Li, Jingxi; Mengu, Deniz; Luo, Yi et al.
CLEO: Science and Innovations, CLEO_SI 2020. Optica Publishing Group (formerly OSA), 2020. SM1E.3 (Optics InfoBase Conference Papers; Vol. Part F183-CLEO-SI 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Improving the inference accuracy of diffractive optical neural networks using class-specific differential detection

AU - Li, Jingxi

AU - Mengu, Deniz

AU - Luo, Yi

AU - Rivenson, Yair

AU - Ozcan, Aydogan

PY - 2020/1/1

Y1 - 2020/1/1

N2 - We report all-optical object classification systems that are based on class-specific design of diffractive neural networks followed by a differential detection scheme. The blind inference accuracies achieved through this framework are significantly enhanced.

AB - We report all-optical object classification systems that are based on class-specific design of diffractive neural networks followed by a differential detection scheme. The blind inference accuracies achieved through this framework are significantly enhanced.

UR - https://www.scopus.com/pages/publications/85095428598

U2 - 10.1364/CLEO_SI.2020.SM1E.3

DO - 10.1364/CLEO_SI.2020.SM1E.3

M3 - Conference contribution

AN - SCOPUS:85095428598

SN - 9781943580767

T3 - Optics InfoBase Conference Papers

BT - CLEO

PB - Optica Publishing Group (formerly OSA)

T2 - CLEO: Science and Innovations, CLEO_SI 2020

Y2 - 10 May 2020 through 15 May 2020

ER -

Improving the inference accuracy of diffractive optical neural networks using class-specific differential detection

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this