Image recognition based on optical reservoir computing

Jiayi Li; Qiang Cai; Pu Li; Yi Yang; K. Alan Shore; Yuncai Wang

doi:10.1063/5.0110838

Image recognition based on optical reservoir computing

Jiayi Li, Qiang Cai, Pu Li, Yi Yang, K. Alan Shore, Yuncai Wang

School of Computer Science & Engineering

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

Abstract

We propose an image recognition approach using a single physical node based optical reservoir computing. Specifically, an optically injected semiconductor laser with self-delayed feedback is used as the reservoir. We perform a handwritten-digit recognition task by greatly increasing the number of virtual nodes in delayed feedback using outputs from multiple delay times. Final simulation results confirm that the recognition accuracy can reach 99\ this scheme may provide a resource-efficient alternative approach to image recognition.

Original language	English
Article number	123106
Journal	Chaos: An Interdisciplinary Journal of Nonlinear Science
Volume	32
Issue number	12
Early online date	1 Dec 2022
DOIs	https://doi.org/10.1063/5.0110838
Publication status	Published - Dec 2022

Access to Document

10.1063/5.0110838

Cite this

@article{a610f20c94b44bf7aa156b851be32ce6,

title = "Image recognition based on optical reservoir computing",

abstract = "We propose an image recognition approach using a single physical node based optical reservoir computing. Specifically, an optically injected semiconductor laser with self-delayed feedback is used as the reservoir. We perform a handwritten-digit recognition task by greatly increasing the number of virtual nodes in delayed feedback using outputs from multiple delay times. Final simulation results confirm that the recognition accuracy can reach 99\textbackslash{} this scheme may provide a resource-efficient alternative approach to image recognition.",

author = "Jiayi Li and Qiang Cai and Pu Li and Yi Yang and \{Alan Shore\}, K. and Yuncai Wang",

year = "2022",

month = dec,

doi = "10.1063/5.0110838",

language = "English",

volume = "32",

journal = "Chaos: An Interdisciplinary Journal of Nonlinear Science",

issn = "1054-1500",

publisher = "American Institute of Physics",

number = "12",

}

TY - JOUR

T1 - Image recognition based on optical reservoir computing

AU - Li, Jiayi

AU - Cai, Qiang

AU - Li, Pu

AU - Yang, Yi

AU - Alan Shore, K.

AU - Wang, Yuncai

PY - 2022/12

Y1 - 2022/12

N2 - We propose an image recognition approach using a single physical node based optical reservoir computing. Specifically, an optically injected semiconductor laser with self-delayed feedback is used as the reservoir. We perform a handwritten-digit recognition task by greatly increasing the number of virtual nodes in delayed feedback using outputs from multiple delay times. Final simulation results confirm that the recognition accuracy can reach 99\ this scheme may provide a resource-efficient alternative approach to image recognition.

AB - We propose an image recognition approach using a single physical node based optical reservoir computing. Specifically, an optically injected semiconductor laser with self-delayed feedback is used as the reservoir. We perform a handwritten-digit recognition task by greatly increasing the number of virtual nodes in delayed feedback using outputs from multiple delay times. Final simulation results confirm that the recognition accuracy can reach 99\ this scheme may provide a resource-efficient alternative approach to image recognition.

U2 - 10.1063/5.0110838

DO - 10.1063/5.0110838

M3 - Article

SN - 1054-1500

VL - 32

JO - Chaos: An Interdisciplinary Journal of Nonlinear Science

JF - Chaos: An Interdisciplinary Journal of Nonlinear Science

IS - 12

M1 - 123106

ER -

Image recognition based on optical reservoir computing

Abstract

Access to Document

Fingerprint

Cite this