Delay-based reservoir computing: tackling performance degradation due to system response time

Abstract

We analyze the degradation of the computational capacity of delay-based reservoir computers due to system response time. We demonstrate that this degradation is reduced when the delay time is greater than the data injection time. Performance improvement is demonstrated on several benchmarking tasks.

© 2020 Optical Society of America

Asymmetrical performance of a laser-based reservoir computer with optoelectronic feedback

P. S. Dmitriev, A. V. Kovalev, A. Locquet, D. Rontani, and E. A. Viktorov
Opt. Lett. 45(22) 6150-6153 (2020)

Enhanced performance of a reservoir computer using polarization dynamics in VCSELs

Jeremy Vatin, Damien Rontani, and Marc Sciamanna
Opt. Lett. 43(18) 4497-4500 (2018)

Prediction performance of reservoir computing systems based on a diode-pumped erbium-doped microchip laser subject to optical feedback

Romain Modeste Nguimdo, Eric Lacot, Olivier Jacquin, Olivier Hugon, Guy Van der Sande, and Hugues Guillet de Chatellus
Opt. Lett. 42(3) 375-378 (2017)

Performance optimization of a reservoir computing system based on a solitary semiconductor laser under electrical-message injection

Qingqing Zeng, Zhengmao Wu, Dianzuo Yue, Xiangsheng Tan, Junyao Tao, and Guangqiong Xia
Appl. Opt. 59(23) 6932-6938 (2020)

Optoelectronic reservoir computing: tackling noise-induced performance degradation

M. C. Soriano, S. Ortín, D. Brunner, L. Larger, C. R. Mirasso, I. Fischer, and L. Pesquera
Opt. Express 21(1) 12-20 (2013)