Summary
International Symposium on Nonlinear Theory and Its Applications
2015
Session Number:A2L-C
Session:
Number:A2L-C-2
Reservoir Computing Using a Chaotic Mask Signal in a Semiconductor Laser with Optical Feedback
Joma Nakayama, Kazutaka Kanno, Atsushi Uchida,
pp.37-40
Publication Date:2015/12/1
Online ISSN:2188-5079
DOI:10.34385/proc.47.A2L-C-2
PDF download (970.7KB)
Summary:
Reservoir computing is a novel computing method inspired by neural network. Recently, despite a simple implementation, delay-based reservoir computing using laser dynamical systems can achieve fast and efficient information processing, such as speech recognition and chaotic time-series prediction. We implement reservoir computing based on consistency of semiconductor lasers subjected to optical delayed-feedback and injection. We also investigate performance improvement with an approach using an analog chaotic mask signal.