Summary

International Symposium on Nonlinear Theory and Its Applications

2016

Session Number:C2L-B

Session:

Number:C2L-B-3

Experiment on Reservoir Computing Using Consistency of a Semiconductor Laser

Yoma Kuriki,  Joma Nakayama,  Kosuke Takano,  Atsushi Uchida,  

pp.-

Publication Date:2016/11/27

Online ISSN:2188-5079

DOI:10.34385/proc.48.C2L-B-3

PDF download (334.1KB)

Summary:
Reservoir computing is an efficient approach for processing time dependent information, such as time series prediction and speech recognition. We experimentally investigate reservoir computing based on the consistency of a semiconductor laser subjected to optical feedback and injection. We investigate the effect of noise of the semiconductor laser on the performance of reservoir computing with a time-series prediction task. The performance can be improved by reducing the amount of the noise.