Handwritten numeral recognition utilizing optoelectronic reservoir computing with double reservoir layers

Wei-Lai Wu; Dian-Zuo Yue; Zheng-Mao Wu; Guang-Qiong Xia

doi:10.1117/12.2601295

9 October 2021 Handwritten numeral recognition utilizing optoelectronic reservoir computing with double reservoir layers

Wei-Lai Wu, Dian-Zuo Yue, Zheng-Mao Wu, Guang-Qiong Xia

Author Affiliations +

Proceedings Volume 11891, Semiconductor Lasers and Applications XI; 118910M (2021) https://doi.org/10.1117/12.2601295
Event: SPIE/COS Photonics Asia, 2021, Nantong, JS, China

Abstract

Optoelectronic reservoir computing (RC) is a supervised training algorithm implanted in an optoelectronic time-delay system, which possesses simple structure and can be utilized to realize pattern recognition. In this work, based on double reservoir layers composed of two Mach-Zehnder modulators (MZMs), a novel optoelectronic RC system is proposed and the system performances for processing handwritten numeral recognition (HNR) are analyzed. For such a system, a masked handwritten numeral information is injected into the first reservoir layer, the different value between two adjacent node states of the first reservoir layer is sent to the second reservoir layer, and the virtual node states of the second reservoir layer are extracted for training and testing. The simulated results show that, by optimizing the system parameters, a word error rate (WER) of 0.11 for processing HNR can be achieved. By comparing with an optoelectronic RC with a single reservoir layer, the optoelectronic RC with two reservoir layers possesses better performances for processing HNR.

Conference Presentation

Citation Download Citation

Wei-Lai Wu, Dian-Zuo Yue, Zheng-Mao Wu, and Guang-Qiong Xia "Handwritten numeral recognition utilizing optoelectronic reservoir computing with double reservoir layers", Proc. SPIE 11891, Semiconductor Lasers and Applications XI, 118910M (9 October 2021); https://doi.org/10.1117/12.2601295

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available