Prediction and classification performance of reservoir computing system using mutually delay-coupled semiconductor lasers

• Published in: Optics communications Vol. 433; pp. 215 - 220
• Main Authors: Hou, Yu-Shuang, Xia, Guang-Qiong, Jayaprasath, Elumalai, Yue, Dian-Zuo, Yang, Wen-Yan, Wu, Zheng-Mao
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.02.2019
• Subjects: Information processing; Optical neural system; Reservoir computing; Semiconductor laser; Optical neural system; Reservoir computing; Information processing; Semiconductor laser
• ISSN: 0030-4018; 1873-0310
• DOI: 10.1016/j.optcom.2018.10.014

A reservoir computing (RC) system based on two mutually delay coupled semiconductor lasers (MDC-SLs) subject to optical injection is proposed, and the chaotic time series prediction and signal classification performance for such a system is numerically investigated via the Santa-Fe time-series prediction task and the signal classification task, respectively. The simulation results indicate that, when adopting this system to process ultra-fast data with rate up to 1 Gbps, the best prediction error 5.1×10−5±5.2×10−6 and signal recognition error 5.5×10−4±8.8×10−5 can be achieved under optimized operation parameters.