On-Chip Quantum Dot Lasers Driven High-Speed Optical Neural Networks

Zhican Zhou; Yuetong Fang; Xiangpeng Ou; William He; Xuhao Wu; Renjing Xu; David Z. Pan; Yating Wan

On-Chip Quantum Dot Lasers Driven High-Speed Optical Neural Networks

Zhican Zhou, Yuetong Fang, Xiangpeng Ou, William He, Xuhao Wu, Renjing Xu, David Z. Pan, Yating Wan^*

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

We present an optical neural network architecture driven by on-chip quantum dot lasers, achieving 3.5 TOPS/mm² theoretical computational density. With an optimized model (reducing programming operations by over 75%), our architecture attains 91.128% MNIST accuracy.

Original language	English (US)
State	Published - 2024
Event	CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics - Charlotte, United States Duration: May 5 2024 → May 10 2024

Conference

Conference	CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics
Country/Territory	United States
City	Charlotte
Period	05/5/24 → 05/10/24

Bibliographical note

Publisher Copyright:
© Optica Publishing Group 2024

ASJC Scopus subject areas

Atomic and Molecular Physics, and Optics
General Computer Science
Space and Planetary Science
Control and Systems Engineering
Electrical and Electronic Engineering
Electronic, Optical and Magnetic Materials
Instrumentation

Cite this

@conference{0705c18b0c3c40a99d071a86f8c5fe96,

title = "On-Chip Quantum Dot Lasers Driven High-Speed Optical Neural Networks",

abstract = "We present an optical neural network architecture driven by on-chip quantum dot lasers, achieving 3.5 TOPS/mm2 theoretical computational density. With an optimized model (reducing programming operations by over 75\%), our architecture attains 91.128\% MNIST accuracy.",

author = "Zhican Zhou and Yuetong Fang and Xiangpeng Ou and William He and Xuhao Wu and Renjing Xu and Pan, \{David Z.\} and Yating Wan",

note = "Publisher Copyright: {\textcopyright} Optica Publishing Group 2024; CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics ; Conference date: 05-05-2024 Through 10-05-2024",

year = "2024",

language = "English (US)",

}

TY - CONF

T1 - On-Chip Quantum Dot Lasers Driven High-Speed Optical Neural Networks

AU - Zhou, Zhican

AU - Fang, Yuetong

AU - Ou, Xiangpeng

AU - He, William

AU - Wu, Xuhao

AU - Xu, Renjing

AU - Pan, David Z.

AU - Wan, Yating

PY - 2024

Y1 - 2024

N2 - We present an optical neural network architecture driven by on-chip quantum dot lasers, achieving 3.5 TOPS/mm2 theoretical computational density. With an optimized model (reducing programming operations by over 75%), our architecture attains 91.128% MNIST accuracy.

AB - We present an optical neural network architecture driven by on-chip quantum dot lasers, achieving 3.5 TOPS/mm2 theoretical computational density. With an optimized model (reducing programming operations by over 75%), our architecture attains 91.128% MNIST accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85205126191&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85205126191

T2 - CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

Y2 - 5 May 2024 through 10 May 2024

ER -

On-Chip Quantum Dot Lasers Driven High-Speed Optical Neural Networks

Abstract

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this