Design of Shift-, Scale- and Rotation Invariant Diffractive Optical Networks

Deniz Mengu; Yair Rivenson; Aydogan Ozcan

Design of Shift-, Scale- and Rotation Invariant Diffractive Optical Networks

Deniz Mengu, Yair Rivenson, Aydogan Ozcan

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

Abstract

We investigate the sensitivity of diffractive optical networks to random object translation, scaling and rotation operations, and present a deep learning-based training strategy to design shift-, scale- and rotation invariant diffractive networks.

Original language	English
Article number	FTh4C.4
Journal	Optics InfoBase Conference Papers
State	Published - 1 Jan 2021
Externally published	Yes
Event	Frontiers in Optics + Laser Science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021 - Virtual, Online, United States Duration: 1 Nov 2021 → 4 Nov 2021

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Mechanics of Materials

Cite this

@article{87db495d60f341df86c7e43d0767e613,

title = "Design of Shift-, Scale- and Rotation Invariant Diffractive Optical Networks",

abstract = "We investigate the sensitivity of diffractive optical networks to random object translation, scaling and rotation operations, and present a deep learning-based training strategy to design shift-, scale- and rotation invariant diffractive networks.",

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

note = "Publisher Copyright: Frontiers in Optics / Laser Science {\textcopyright} Optica Publishing Group 2021.; Frontiers in Optics + Laser Science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021 ; Conference date: 01-11-2021 Through 04-11-2021",

year = "2021",

month = jan,

day = "1",

language = "English",

journal = "Optics InfoBase Conference Papers",

issn = "2162-2701",

}

TY - JOUR

T1 - Design of Shift-, Scale- and Rotation Invariant Diffractive Optical Networks

AU - Mengu, Deniz

AU - Rivenson, Yair

AU - Ozcan, Aydogan

N1 - Publisher Copyright: Frontiers in Optics / Laser Science © Optica Publishing Group 2021.

PY - 2021/1/1

Y1 - 2021/1/1

N2 - We investigate the sensitivity of diffractive optical networks to random object translation, scaling and rotation operations, and present a deep learning-based training strategy to design shift-, scale- and rotation invariant diffractive networks.

AB - We investigate the sensitivity of diffractive optical networks to random object translation, scaling and rotation operations, and present a deep learning-based training strategy to design shift-, scale- and rotation invariant diffractive networks.

UR - https://www.scopus.com/pages/publications/85130216429

M3 - Conference article

AN - SCOPUS:85130216429

SN - 2162-2701

JO - Optics InfoBase Conference Papers

JF - Optics InfoBase Conference Papers

M1 - FTh4C.4

T2 - Frontiers in Optics + Laser Science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021

Y2 - 1 November 2021 through 4 November 2021

ER -

Design of Shift-, Scale- and Rotation Invariant Diffractive Optical Networks

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this