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

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

Electrical and Computer Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

1 Citation (Scopus)

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.

Original language	English
Title of host publication	2022 Optical Fiber Communications Conference and Exhibition (OFC)
Editors	Domiique Dagenais
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Number of pages	3
ISBN (Electronic)	9781557524669
ISBN (Print)	9781665470124
Publication status	Published - 2022
Event	Optical Fiber Communications Conference and Exhibition 2022 - San Diego, United States of America Duration: 6 Mar 2022 → 10 Mar 2022 https://ieeexplore.ieee.org/xpl/conhome/9748173/proceeding (Proceedings)

Publication series

Name	Optics InfoBase Conference Papers

Conference

Conference	Optical Fiber Communications Conference and Exhibition 2022
Abbreviated title	OFC 2022
Country/Territory	United States of America
City	San Diego
Period	6/03/22 → 10/03/22
Internet address	https://ieeexplore.ieee.org/xpl/conhome/9748173/proceeding (Proceedings)

Access to Document

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

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 D. Dagenais (Ed.), 2022 Optical Fiber Communications Conference and Exhibition (OFC) Article Tu3G.1 (Optics InfoBase Conference Papers). IEEE, Institute of Electrical and Electronics Engineers. https://ieeexplore.ieee.org/document/9748246

@inproceedings{a791a3ff5a4e4fd1a514bf957d0eee69,

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.",

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.\}",

note = "Publisher Copyright: {\textcopyright} Optica Publishing Group 2022, {\textcopyright} 2022 The Author(s); Optical Fiber Communications Conference and Exhibition 2022, OFC 2022 ; Conference date: 06-03-2022 Through 10-03-2022",

year = "2022",

language = "English",

isbn = "9781665470124",

series = "Optics InfoBase Conference Papers",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

editor = "Domiique Dagenais",

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

address = "United States of America",

url = "https://ieeexplore.ieee.org/xpl/conhome/9748173/proceeding",

}

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 D Dagenais (ed.), 2022 Optical Fiber Communications Conference and Exhibition (OFC)., Tu3G.1, Optics InfoBase Conference Papers, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, Optical Fiber Communications Conference and Exhibition 2022, San Diego, California, United States of America, 6/03/22. <https://ieeexplore.ieee.org/document/9748246>

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). ed. / Domiique Dagenais. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2022. Tu3G.1 (Optics InfoBase Conference Papers).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

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.

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.

UR - https://www.scopus.com/pages/publications/85168058966

M3 - Conference Paper

AN - SCOPUS:85168058966

SN - 9781665470124

T3 - Optics InfoBase Conference Papers

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

A2 - Dagenais, Domiique

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - Optical Fiber Communications Conference and Exhibition 2022

Y2 - 6 March 2022 through 10 March 2022

ER -

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

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this