Optical neuromorphic processing based on Kerr microcombs

X. Xu; M. Tan; J. Wu; A. Boes; B. Corcoran; T. Nguyen; S. T. Chu; B. E. Little; R. Morandotti; A. Mitchell; D. Hicks; D. J. Moss

doi:10.1364/CLEO_SI.2021.AW2E.4

Optical neuromorphic processing based on Kerr microcombs

X. Xu, M. Tan, J. Wu, A. Boes, B. Corcoran, T. Nguyen, S. T. Chu, B. E. Little, R. Morandotti, A. Mitchell, D. Hicks, D. J. Moss

Electrical and Computer Systems Engineering

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

Abstract

We report a new approach to ONNs based on integrated Kerr micro-combs that is programmable, highly scalable and capable of reaching ultra-high speeds. We demonstrate a single neuron perceptron at 11.9 Giga-OPS at 8 bits per OP, or 95.2 Gbps. We then demonstrate a convolutional accelerator operating beyond 11 TeraOPs/s. We test the perceptron on handwritten-digit recognition and cancer-cell detection-achieving over 90% and 85% accuracy, respectively.

Original language	English
Title of host publication	2021 Conference on Lasers and Electro-Optics, CLEO 2021 - Proceedings
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Number of pages	2
ISBN (Electronic)	9781943580910
DOIs	https://doi.org/10.1364/CLEO_SI.2021.AW2E.4
Publication status	Published - 2021
Event	Conference on Lasers and Electro-Optics 2021 - Online, San Jose, United States of America Duration: 9 May 2021 → 14 May 2021 https://opg.optica.org/conference.cfm?meetingid=124&yr=2021#AW2E (Proceedings)

Conference

Conference	Conference on Lasers and Electro-Optics 2021
Abbreviated title	CLEO 2021
Country/Territory	United States of America
City	San Jose
Period	9/05/21 → 14/05/21
Internet address	https://opg.optica.org/conference.cfm?meetingid=124&yr=2021#AW2E (Proceedings)

Access to Document

10.1364/CLEO_SI.2021.AW2E.4

Cite this

Xu, X., Tan, M., Wu, J., Boes, A., Corcoran, B., Nguyen, T., Chu, S. T., Little, B. E., Morandotti, R., Mitchell, A., Hicks, D., & Moss, D. J. (2021). Optical neuromorphic processing based on Kerr microcombs. In 2021 Conference on Lasers and Electro-Optics, CLEO 2021 - Proceedings IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1364/CLEO_SI.2021.AW2E.4

@inproceedings{9eac21c8f3ce496dadb8b7fe70b9c8a9,

title = "Optical neuromorphic processing based on Kerr microcombs",

abstract = "We report a new approach to ONNs based on integrated Kerr micro-combs that is programmable, highly scalable and capable of reaching ultra-high speeds. We demonstrate a single neuron perceptron at 11.9 Giga-OPS at 8 bits per OP, or 95.2 Gbps. We then demonstrate a convolutional accelerator operating beyond 11 TeraOPs/s. We test the perceptron on handwritten-digit recognition and cancer-cell detection-achieving over 90% and 85% accuracy, respectively. ",

author = "X. Xu and M. Tan and J. Wu and A. Boes and B. Corcoran and T. Nguyen and Chu, {S. T.} and Little, {B. E.} and R. Morandotti and A. Mitchell and D. Hicks and Moss, {D. J.}",

note = "Publisher Copyright: {\textcopyright} 2021 OSA.; Conference on Lasers and Electro-Optics 2021, CLEO 2021 ; Conference date: 09-05-2021 Through 14-05-2021",

year = "2021",

doi = "10.1364/CLEO_SI.2021.AW2E.4",

language = "English",

booktitle = "2021 Conference on Lasers and Electro-Optics, CLEO 2021 - Proceedings",

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

address = "United States of America",

url = "https://opg.optica.org/conference.cfm?meetingid=124&yr=2021#AW2E",

}

Xu, X, Tan, M, Wu, J, Boes, A, Corcoran, B, Nguyen, T, Chu, ST, Little, BE, Morandotti, R, Mitchell, A, Hicks, D & Moss, DJ 2021, Optical neuromorphic processing based on Kerr microcombs. in 2021 Conference on Lasers and Electro-Optics, CLEO 2021 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, Conference on Lasers and Electro-Optics 2021, San Jose, California, United States of America, 9/05/21. https://doi.org/10.1364/CLEO_SI.2021.AW2E.4

Optical neuromorphic processing based on Kerr microcombs. / Xu, X.; Tan, M.; Wu, J.; Boes, A.; Corcoran, B.; Nguyen, T.; Chu, S. T.; Little, B. E.; Morandotti, R.; Mitchell, A.; Hicks, D.; Moss, D. J.

2021 Conference on Lasers and Electro-Optics, CLEO 2021 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2021.

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

TY - GEN

T1 - Optical neuromorphic processing based on Kerr microcombs

AU - Xu, X.

AU - Tan, M.

AU - Wu, J.

AU - Boes, A.

AU - Corcoran, B.

AU - Nguyen, T.

AU - Chu, S. T.

AU - Little, B. E.

AU - Morandotti, R.

AU - Mitchell, A.

AU - Hicks, D.

AU - Moss, D. J.

PY - 2021

Y1 - 2021

N2 - We report a new approach to ONNs based on integrated Kerr micro-combs that is programmable, highly scalable and capable of reaching ultra-high speeds. We demonstrate a single neuron perceptron at 11.9 Giga-OPS at 8 bits per OP, or 95.2 Gbps. We then demonstrate a convolutional accelerator operating beyond 11 TeraOPs/s. We test the perceptron on handwritten-digit recognition and cancer-cell detection-achieving over 90% and 85% accuracy, respectively.

AB - We report a new approach to ONNs based on integrated Kerr micro-combs that is programmable, highly scalable and capable of reaching ultra-high speeds. We demonstrate a single neuron perceptron at 11.9 Giga-OPS at 8 bits per OP, or 95.2 Gbps. We then demonstrate a convolutional accelerator operating beyond 11 TeraOPs/s. We test the perceptron on handwritten-digit recognition and cancer-cell detection-achieving over 90% and 85% accuracy, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85120474349&partnerID=8YFLogxK

U2 - 10.1364/CLEO_SI.2021.AW2E.4

DO - 10.1364/CLEO_SI.2021.AW2E.4

M3 - Conference Paper

AN - SCOPUS:85120474349

BT - 2021 Conference on Lasers and Electro-Optics, CLEO 2021 - Proceedings

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - Conference on Lasers and Electro-Optics 2021

Y2 - 9 May 2021 through 14 May 2021

ER -

Optical neuromorphic processing based on Kerr microcombs

Abstract

Conference

Access to Document

Other files and links

Cite this