Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs

Mengxi Tan; Xingyuan Xu; Jiayang Wu; Andreas Boes; Bill Corcoran; Thach G. Nguyen; Sai T. Chu; Brent E. Little; Damien G. Hicks; Roberto Morandotti; Arnan Mitchell; David J. Moss

doi:10.1364/OFC.2022.Tu3G.1

Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs

Mengxi Tan, Xingyuan Xu, Jiayang Wu, Andreas Boes, Bill Corcoran, Thach G. Nguyen, Sai T. Chu, Brent E. Little, Damien G. Hicks, Roberto Morandotti, Arnan Mitchell, David J. Moss^*

^*Corresponding author for this work

Department of Physics

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

We demonstrate a universal optical vector convolutional accelerator operating at 11 Tera-OPS, generating convolutions of images of 250,000 pixels with 8-bit resolution for 10 kernels simultaneously. We use the same hardware to form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 88% accuracy. Our approach is scalable and trainable for applications to unmanned vehicle and real-time video recognition. © Optica Publishing Group 2022, © 2022 The Author(s)

Original language	English
Title of host publication	2022 Optical Fiber Communications Conference and Exhibition (OFC)
Subtitle of host publication	Proceedings
Publisher	IEEE
ISBN (Electronic)	9781557524669
ISBN (Print)	9781665470124
DOIs	https://doi.org/10.1364/OFC.2022.Tu3G.1
Publication status	Published - 2022
Event	2022 Optical Fiber Communications Conference and Exhibition (OFC 2022) - San Diego Convention Center, San Diego, United States Duration: 6 Mar 2022 → 10 Mar 2022 https://www.ofcconference.org/en-us/home/schedule/

Publication series

Name	Optics InfoBase Conference Papers

Name	Optical Fiber Communications Conference and Exhibition, OFC - Proceedings

Conference

Conference	2022 Optical Fiber Communications Conference and Exhibition (OFC 2022)
Place	United States
City	San Diego
Period	6/03/22 → 10/03/22
Internet address	https://www.ofcconference.org/en-us/home/schedule/

Access Output

10.1364/OFC.2022.Tu3G.1

https://ieeexplore.ieee.org/document/9748246

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Tan, M., Xu, X., Wu, J., Boes, A., Corcoran, B., Nguyen, T. G., Chu, S. T., Little, B. E., Hicks, D. G., Morandotti, R., Mitchell, A., & Moss, D. J. (2022). Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs. In 2022 Optical Fiber Communications Conference and Exhibition (OFC): Proceedings Article Tu3G.1 (Optics InfoBase Conference Papers), (Optical Fiber Communications Conference and Exhibition, OFC - Proceedings). IEEE. https://doi.org/10.1364/OFC.2022.Tu3G.1

@inproceedings{7c26964fe32d442387fc21a0ca5657ef,

title = "Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs",

abstract = "We demonstrate a universal optical vector convolutional accelerator operating at 11 Tera-OPS, generating convolutions of images of 250,000 pixels with 8-bit resolution for 10 kernels simultaneously. We use the same hardware to form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 88% accuracy. Our approach is scalable and trainable for applications to unmanned vehicle and real-time video recognition. {\textcopyright} Optica Publishing Group 2022, {\textcopyright} 2022 The Author(s)",

author = "Mengxi Tan and Xingyuan Xu and Jiayang Wu and Andreas Boes and Bill Corcoran and Nguyen, {Thach G.} and Chu, {Sai T.} and Little, {Brent E.} and Hicks, {Damien G.} and Roberto Morandotti and Arnan Mitchell and Moss, {David J.}",

year = "2022",

doi = "10.1364/OFC.2022.Tu3G.1",

language = "English",

isbn = "9781665470124",

series = "Optics InfoBase Conference Papers",

publisher = "IEEE",

booktitle = "2022 Optical Fiber Communications Conference and Exhibition (OFC)",

address = "United States",

note = "2022 Optical Fiber Communications Conference and Exhibition (OFC 2022) ; Conference date: 06-03-2022 Through 10-03-2022",

url = "https://www.ofcconference.org/en-us/home/schedule/",

}

Tan, M, Xu, X, Wu, J, Boes, A, Corcoran, B, Nguyen, TG, Chu, ST, Little, BE, Hicks, DG, Morandotti, R, Mitchell, A & Moss, DJ 2022, Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs. in 2022 Optical Fiber Communications Conference and Exhibition (OFC): Proceedings., Tu3G.1, Optics InfoBase Conference Papers, Optical Fiber Communications Conference and Exhibition, OFC - Proceedings, IEEE, 2022 Optical Fiber Communications Conference and Exhibition (OFC 2022), San Diego, United States, 6/03/22. https://doi.org/10.1364/OFC.2022.Tu3G.1

Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs. / Tan, Mengxi; Xu, Xingyuan; Wu, Jiayang et al.
2022 Optical Fiber Communications Conference and Exhibition (OFC): Proceedings. IEEE, 2022. Tu3G.1 (Optics InfoBase Conference Papers), (Optical Fiber Communications Conference and Exhibition, OFC - Proceedings).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs

AU - Tan, Mengxi

AU - Xu, Xingyuan

AU - Wu, Jiayang

AU - Boes, Andreas

AU - Corcoran, Bill

AU - Nguyen, Thach G.

AU - Chu, Sai T.

AU - Little, Brent E.

AU - Hicks, Damien G.

AU - Morandotti, Roberto

AU - Mitchell, Arnan

AU - Moss, David J.

PY - 2022

Y1 - 2022

N2 - We demonstrate a universal optical vector convolutional accelerator operating at 11 Tera-OPS, generating convolutions of images of 250,000 pixels with 8-bit resolution for 10 kernels simultaneously. We use the same hardware to form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 88% accuracy. Our approach is scalable and trainable for applications to unmanned vehicle and real-time video recognition. © Optica Publishing Group 2022, © 2022 The Author(s)

AB - We demonstrate a universal optical vector convolutional accelerator operating at 11 Tera-OPS, generating convolutions of images of 250,000 pixels with 8-bit resolution for 10 kernels simultaneously. We use the same hardware to form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 88% accuracy. Our approach is scalable and trainable for applications to unmanned vehicle and real-time video recognition. © Optica Publishing Group 2022, © 2022 The Author(s)

UR - http://www.scopus.com/inward/record.url?scp=85128886324&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85128886324&origin=recordpage

U2 - 10.1364/OFC.2022.Tu3G.1

DO - 10.1364/OFC.2022.Tu3G.1

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781665470124

T3 - Optics InfoBase Conference Papers

BT - 2022 Optical Fiber Communications Conference and Exhibition (OFC)

PB - IEEE

T2 - 2022 Optical Fiber Communications Conference and Exhibition (OFC 2022)

Y2 - 6 March 2022 through 10 March 2022

ER -

Tan M, Xu X, Wu J, Boes A, Corcoran B, Nguyen TG et al. Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs. In 2022 Optical Fiber Communications Conference and Exhibition (OFC): Proceedings. IEEE. 2022. Tu3G.1. (Optics InfoBase Conference Papers). (Optical Fiber Communications Conference and Exhibition, OFC - Proceedings). Epub 2022 Apr 13. doi: 10.1364/OFC.2022.Tu3G.1

Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this