Abstract
During the last decade reservoir computing (RC) has proven to be a powerful machine learning concept using recurrent networks to process sequential information streams [1]. Lately, the concept of RC was drastically simplified to reduce hardware requirements, thus making machine learning concepts more obtainable to apply in actual physical systems [2]. RC has been implemented in photonic configurations and has efficiently processed analog optical signals following simple schemes and minimal training overhead. Especially the realization using a semiconductor laser with time-delayed optical feedback has shown the potential of all-optical machine learning, utilizing signals with transient states at the GHz regime [3].
© 2017 IEEE
PDF ArticleMore Like This
Stephan Pachnicke and Shi Li
T1B.3 Asia Communications and Photonics Conference (ACP) 2020
Yuanli Yue, Shouju Liu, Yue Feng, and Chao Wang
JW3B.109 CLEO: Applications and Technology (CLEO:A&T) 2022
Mariia Sorokina, Sergey Sergeyev, and Sergei Turitsyn
NpTh4G.5 Nonlinear Photonics (NP) 2018