Tunable nonlinear activation functions for optical neural networks

Ian A.D. Williamson; Tyler W. Hughes; Momchil Minkov; Ben Bartlett; Sunil Pai; Shanhui Fan

doi:10.1364/CLEO_SI.2020.SM1E.2

Tunable nonlinear activation functions for optical neural networks

Ian A.D. Williamson, Tyler W. Hughes, Momchil Minkov, Ben Bartlett, Sunil Pai, Shanhui Fan

Stanford University

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

Abstract

We introduce an electro-optic hardware platform for realizing optical nonlinearities and demonstrate that, as a nonlinear activation function, it can substantially improve the classification performance of optical neural networks.

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.2
Publication status	Published - 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

Access to Document

10.1364/CLEO_SI.2020.SM1E.2

Cite this

Williamson, I. A. D., Hughes, T. W., Minkov, M., Bartlett, B., Pai, S., & Fan, S. (2020). Tunable nonlinear activation functions for optical neural networks. In CLEO: Science and Innovations, CLEO_SI 2020 Article SM1E.2 (Optics InfoBase Conference Papers; Vol. Part F183-CLEO-SI 2020). Optica Publishing Group (formerly OSA). https://doi.org/10.1364/CLEO_SI.2020.SM1E.2

@inproceedings{9aa5c1181e3048b4a8561e3aacf2f83e,

title = "Tunable nonlinear activation functions for optical neural networks",

abstract = "We introduce an electro-optic hardware platform for realizing optical nonlinearities and demonstrate that, as a nonlinear activation function, it can substantially improve the classification performance of optical neural networks.",

author = "Williamson, {Ian A.D.} and Hughes, {Tyler W.} and Momchil Minkov and Ben Bartlett and Sunil Pai and Shanhui Fan",

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",

doi = "10.1364/CLEO_SI.2020.SM1E.2",

language = "English",

isbn = "9781943580767",

series = "Optics InfoBase Conference Papers",

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

booktitle = "CLEO",

}

Williamson, IAD, Hughes, TW, Minkov, M, Bartlett, B, Pai, S & Fan, S 2020, Tunable nonlinear activation functions for optical neural networks. in CLEO: Science and Innovations, CLEO_SI 2020., SM1E.2, 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.2

Tunable nonlinear activation functions for optical neural networks. / Williamson, Ian A.D.; Hughes, Tyler W.; Minkov, Momchil et al.
CLEO: Science and Innovations, CLEO_SI 2020. Optica Publishing Group (formerly OSA), 2020. SM1E.2 (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 - Tunable nonlinear activation functions for optical neural networks

AU - Williamson, Ian A.D.

AU - Hughes, Tyler W.

AU - Minkov, Momchil

AU - Bartlett, Ben

AU - Pai, Sunil

AU - Fan, Shanhui

PY - 2020

Y1 - 2020

N2 - We introduce an electro-optic hardware platform for realizing optical nonlinearities and demonstrate that, as a nonlinear activation function, it can substantially improve the classification performance of optical neural networks.

AB - We introduce an electro-optic hardware platform for realizing optical nonlinearities and demonstrate that, as a nonlinear activation function, it can substantially improve the classification performance of optical neural networks.

UR - http://www.scopus.com/inward/record.url?scp=85095437613&partnerID=8YFLogxK

U2 - 10.1364/CLEO_SI.2020.SM1E.2

DO - 10.1364/CLEO_SI.2020.SM1E.2

M3 - Conference contribution

AN - SCOPUS:85095437613

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 -

Tunable nonlinear activation functions for optical neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this