Inference in artificial intelligence with deep optics and photonics

Gordon Wetzstein; Aydogan Ozcan; Sylvain Gigan; Shanhui Fan; Dirk Englund; Marin Soljačić; Cornelia Denz; David A.B. Miller; Demetri Psaltis

doi:10.1038/s41586-020-2973-6

Inference in artificial intelligence with deep optics and photonics

Gordon Wetzstein, Aydogan Ozcan, Sylvain Gigan, Shanhui Fan, Dirk Englund, Marin Soljačić, Cornelia Denz, David A.B. Miller, Demetri Psaltis

Research output: Contribution to journal › Article › peer-review

561 Scopus citations

Abstract

Artificial intelligence tasks across numerous applications require accelerators for fast and low-power execution. Optical computing systems may be able to meet these domain-specific needs but, despite half a century of research, general-purpose optical computing systems have yet to mature into a practical technology. Artificial intelligence inference, however, especially for visual computing applications, may offer opportunities for inference based on optical and photonic systems. In this Perspective, we review recent work on optical computing for artificial intelligence applications and discuss its promise and challenges.

Original language	English (US)
Pages (from-to)	39-47
Number of pages	9
Journal	Nature
Volume	588
Issue number	7836
DOIs	https://doi.org/10.1038/s41586-020-2973-6
State	Published - Dec 2 2020
Externally published	Yes

Bibliographical note

KAUST Repository Item: Exported on 2022-06-14
Acknowledgements: We thank E. Otte for help designing figures. G.W. was supported by an NSF CAREER Award (IIS 1553333), a Sloan Fellowship, by the KAUST Office of Sponsored Research through the Visual Computing Center CCF grant, and a PECASE by the US Army Research Office. A.O. was supported by an NSF ERC (PATHS-UP) grant. S.G. acknowledges funding from the European Research Council (ERC; H2020, SMARTIES-724473) and support from the Institut Universitaire de France. S.F. was supported by the US Air Force Office of Scientific Research (AFOSR) through the MURI project (grant no. FA9550-17-1-0002). D.E. and M.S. were in part supported by the US Army Research Office through the Institute for Soldier Nanotechnologies (grant no. W911NF-18-2-0048). D.E. also acknowledges support from an NSF EAGER programme. D.A.B.M. was supported by the Air Force Office of Scientific Research (award no. FA9550-17-1-0002). P.D. acknowledges discussions and a long-term collaboration with N. Farhat.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

ASJC Scopus subject areas

General

Access to Document

10.1038/s41586-020-2973-6

Cite this

@article{a447700e9ba446a29036b66225480fae,

title = "Inference in artificial intelligence with deep optics and photonics",

abstract = "Artificial intelligence tasks across numerous applications require accelerators for fast and low-power execution. Optical computing systems may be able to meet these domain-specific needs but, despite half a century of research, general-purpose optical computing systems have yet to mature into a practical technology. Artificial intelligence inference, however, especially for visual computing applications, may offer opportunities for inference based on optical and photonic systems. In this Perspective, we review recent work on optical computing for artificial intelligence applications and discuss its promise and challenges.",

author = "Gordon Wetzstein and Aydogan Ozcan and Sylvain Gigan and Shanhui Fan and Dirk Englund and Marin Solja{\v c}i{\'c} and Cornelia Denz and Miller, {David A.B.} and Demetri Psaltis",

note = "KAUST Repository Item: Exported on 2022-06-14 Acknowledgements: We thank E. Otte for help designing figures. G.W. was supported by an NSF CAREER Award (IIS 1553333), a Sloan Fellowship, by the KAUST Office of Sponsored Research through the Visual Computing Center CCF grant, and a PECASE by the US Army Research Office. A.O. was supported by an NSF ERC (PATHS-UP) grant. S.G. acknowledges funding from the European Research Council (ERC; H2020, SMARTIES-724473) and support from the Institut Universitaire de France. S.F. was supported by the US Air Force Office of Scientific Research (AFOSR) through the MURI project (grant no. FA9550-17-1-0002). D.E. and M.S. were in part supported by the US Army Research Office through the Institute for Soldier Nanotechnologies (grant no. W911NF-18-2-0048). D.E. also acknowledges support from an NSF EAGER programme. D.A.B.M. was supported by the Air Force Office of Scientific Research (award no. FA9550-17-1-0002). P.D. acknowledges discussions and a long-term collaboration with N. Farhat. This publication acknowledges KAUST support, but has no KAUST affiliated authors.",

year = "2020",

month = dec,

day = "2",

doi = "10.1038/s41586-020-2973-6",

language = "English (US)",

volume = "588",

pages = "39--47",

journal = "Nature",

issn = "1476-4687",

publisher = "Nature Research",

number = "7836",

}

TY - JOUR

T1 - Inference in artificial intelligence with deep optics and photonics

AU - Wetzstein, Gordon

AU - Ozcan, Aydogan

AU - Gigan, Sylvain

AU - Fan, Shanhui

AU - Englund, Dirk

AU - Soljačić, Marin

AU - Denz, Cornelia

AU - Miller, David A.B.

AU - Psaltis, Demetri

N1 - KAUST Repository Item: Exported on 2022-06-14 Acknowledgements: We thank E. Otte for help designing figures. G.W. was supported by an NSF CAREER Award (IIS 1553333), a Sloan Fellowship, by the KAUST Office of Sponsored Research through the Visual Computing Center CCF grant, and a PECASE by the US Army Research Office. A.O. was supported by an NSF ERC (PATHS-UP) grant. S.G. acknowledges funding from the European Research Council (ERC; H2020, SMARTIES-724473) and support from the Institut Universitaire de France. S.F. was supported by the US Air Force Office of Scientific Research (AFOSR) through the MURI project (grant no. FA9550-17-1-0002). D.E. and M.S. were in part supported by the US Army Research Office through the Institute for Soldier Nanotechnologies (grant no. W911NF-18-2-0048). D.E. also acknowledges support from an NSF EAGER programme. D.A.B.M. was supported by the Air Force Office of Scientific Research (award no. FA9550-17-1-0002). P.D. acknowledges discussions and a long-term collaboration with N. Farhat. This publication acknowledges KAUST support, but has no KAUST affiliated authors.

PY - 2020/12/2

Y1 - 2020/12/2

N2 - Artificial intelligence tasks across numerous applications require accelerators for fast and low-power execution. Optical computing systems may be able to meet these domain-specific needs but, despite half a century of research, general-purpose optical computing systems have yet to mature into a practical technology. Artificial intelligence inference, however, especially for visual computing applications, may offer opportunities for inference based on optical and photonic systems. In this Perspective, we review recent work on optical computing for artificial intelligence applications and discuss its promise and challenges.

AB - Artificial intelligence tasks across numerous applications require accelerators for fast and low-power execution. Optical computing systems may be able to meet these domain-specific needs but, despite half a century of research, general-purpose optical computing systems have yet to mature into a practical technology. Artificial intelligence inference, however, especially for visual computing applications, may offer opportunities for inference based on optical and photonic systems. In this Perspective, we review recent work on optical computing for artificial intelligence applications and discuss its promise and challenges.

UR - http://hdl.handle.net/10754/679002

UR - http://www.nature.com/articles/s41586-020-2973-6

UR - http://www.scopus.com/inward/record.url?scp=85097030572&partnerID=8YFLogxK

U2 - 10.1038/s41586-020-2973-6

DO - 10.1038/s41586-020-2973-6

M3 - Article

SN - 1476-4687

VL - 588

SP - 39

EP - 47

JO - Nature

JF - Nature

IS - 7836

ER -

Inference in artificial intelligence with deep optics and photonics

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this