Chaotic time-series predicting using optoelectronic reservoir computing

Guizheng Guan; Jianglong Zhuang; Bin Liu

doi:10.1117/12.3036193

8 November 2024 Chaotic time-series predicting using optoelectronic reservoir computing

Guizheng Guan, Jianglong Zhuang, Bin Liu

Proceedings Volume 13233, Semiconductor Lasers and Applications XIV; 1323314 (2024) https://doi.org/10.1117/12.3036193
Event: SPIE/COS Photonics Asia, 2024, Nantong, Jiangsu, China

Conference Poster

Abstract

Reserve computing, inspired by the brain's information-processing capabilities, is well suited for tasks that deal with time-related data. Recently, optoelectronic reservoir computing using a semiconductor laser with optical feedback and optical injection as single nonlinear node architecture has gained significant attention. By introducing mask preprocessing into the data, machine learning methods that leverage the nonlinear dynamics of semiconductor lasers for information processing have become widely recognized. However, while the reservoir computing structure appears simple, it is challenging to understand the data variations. In this paper, we conduct numerical simulations of the model, simply expound on the data flow within the system, and complete the task of short-term chaotic time-series prediction.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Guizheng Guan, Jianglong Zhuang, and Bin Liu "Chaotic time-series predicting using optoelectronic reservoir computing", Proc. SPIE 13233, Semiconductor Lasers and Applications XIV, 1323314 (8 November 2024); https://doi.org/10.1117/12.3036193

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