Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor

Eyal Cohen; Dror Malka; Amir Shemer; Asaf Shahmoon; Michael London; Zeev Zalevsky

doi:10.1117/12.2253426

Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor

Eyal Cohen, Dror Malka, Amir Shemer, Asaf Shahmoon, Michael London, Zeev Zalevsky

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

Abstract

Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a DMD based approaches to realize energetically efficient light coupling into a multi-core fiber realizing a unique design for in-fiber optical neural networks. Neurons and synapses are realized as individual cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in Erbium-doped cores mimics synaptic interactions. In order to dynamically and efficiently couple light into the multi-core fiber a DMD based micro mirror device is used to perform proper beam shaping operation. The beam shaping reshapes the light into a large set of points in space matching the positions of the required cores in the entrance plane to the multi-core fiber.

Original language	English
Title of host publication	Emerging Digital Micromirror Device Based Systems and Applications IX
Editors	Michael R. Douglass, Benjamin L. Lee
Publisher	SPIE
ISBN (Electronic)	9781510606753
DOIs	https://doi.org/10.1117/12.2253426
State	Published - 2017
Event	Emerging Digital Micromirror Device Based Systems and Applications IX - San Francisco, United States Duration: 30 Jan 2017 → 31 Jan 2017

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	10117
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	Emerging Digital Micromirror Device Based Systems and Applications IX
Country/Territory	United States
City	San Francisco
Period	30/01/17 → 31/01/17

Bibliographical note

Publisher Copyright:
© 2017 SPIE.

Keywords

Neural networks
beam shaping
multi-core fiber
optical computing

Access to Document

10.1117/12.2253426

Cite this

Cohen, E., Malka, D., Shemer, A., Shahmoon, A., London, M., & Zalevsky, Z. (2017). Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor. In M. R. Douglass, & B. L. Lee (Eds.), Emerging Digital Micromirror Device Based Systems and Applications IX Article 1011703 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10117). SPIE. https://doi.org/10.1117/12.2253426

@inproceedings{3f990f4e21ce43ceb1dea072f1341f20,

title = "Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor",

abstract = "Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a DMD based approaches to realize energetically efficient light coupling into a multi-core fiber realizing a unique design for in-fiber optical neural networks. Neurons and synapses are realized as individual cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in Erbium-doped cores mimics synaptic interactions. In order to dynamically and efficiently couple light into the multi-core fiber a DMD based micro mirror device is used to perform proper beam shaping operation. The beam shaping reshapes the light into a large set of points in space matching the positions of the required cores in the entrance plane to the multi-core fiber.",

keywords = "Neural networks, beam shaping, multi-core fiber, optical computing",

author = "Eyal Cohen and Dror Malka and Amir Shemer and Asaf Shahmoon and Michael London and Zeev Zalevsky",

note = "Publisher Copyright: {\textcopyright} 2017 SPIE.; Emerging Digital Micromirror Device Based Systems and Applications IX ; Conference date: 30-01-2017 Through 31-01-2017",

year = "2017",

doi = "10.1117/12.2253426",

language = "אנגלית",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Douglass, \{Michael R.\} and Lee, \{Benjamin L.\}",

booktitle = "Emerging Digital Micromirror Device Based Systems and Applications IX",

address = "ארצות הברית",

}

Cohen, E, Malka, D, Shemer, A, Shahmoon, A, London, M & Zalevsky, Z 2017, Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor. in MR Douglass & BL Lee (eds), Emerging Digital Micromirror Device Based Systems and Applications IX., 1011703, Proceedings of SPIE - The International Society for Optical Engineering, vol. 10117, SPIE, Emerging Digital Micromirror Device Based Systems and Applications IX, San Francisco, United States, 30/01/17. https://doi.org/10.1117/12.2253426

Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor. / Cohen, Eyal; Malka, Dror; Shemer, Amir et al.
Emerging Digital Micromirror Device Based Systems and Applications IX. ed. / Michael R. Douglass; Benjamin L. Lee. SPIE, 2017. 1011703 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10117).

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

TY - GEN

T1 - Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor

AU - Cohen, Eyal

AU - Malka, Dror

AU - Shemer, Amir

AU - Shahmoon, Asaf

AU - London, Michael

AU - Zalevsky, Zeev

PY - 2017

Y1 - 2017

N2 - Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a DMD based approaches to realize energetically efficient light coupling into a multi-core fiber realizing a unique design for in-fiber optical neural networks. Neurons and synapses are realized as individual cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in Erbium-doped cores mimics synaptic interactions. In order to dynamically and efficiently couple light into the multi-core fiber a DMD based micro mirror device is used to perform proper beam shaping operation. The beam shaping reshapes the light into a large set of points in space matching the positions of the required cores in the entrance plane to the multi-core fiber.

AB - Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a DMD based approaches to realize energetically efficient light coupling into a multi-core fiber realizing a unique design for in-fiber optical neural networks. Neurons and synapses are realized as individual cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in Erbium-doped cores mimics synaptic interactions. In order to dynamically and efficiently couple light into the multi-core fiber a DMD based micro mirror device is used to perform proper beam shaping operation. The beam shaping reshapes the light into a large set of points in space matching the positions of the required cores in the entrance plane to the multi-core fiber.

KW - Neural networks

KW - beam shaping

KW - multi-core fiber

KW - optical computing

UR - https://www.scopus.com/pages/publications/85019059063

U2 - 10.1117/12.2253426

DO - 10.1117/12.2253426

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85019059063

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Emerging Digital Micromirror Device Based Systems and Applications IX

A2 - Douglass, Michael R.

A2 - Lee, Benjamin L.

PB - SPIE

T2 - Emerging Digital Micromirror Device Based Systems and Applications IX

Y2 - 30 January 2017 through 31 January 2017

ER -

Cohen E, Malka D, Shemer A, Shahmoon A, London M, Zalevsky Z. Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor. In Douglass MR, Lee BL, editors, Emerging Digital Micromirror Device Based Systems and Applications IX. SPIE. 2017. 1011703. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2253426

Micro mirrors based coupling of light to multi-core fiber realizing in-fiber photonic neural network processor

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this