Open AccessReservoir computing system with double optoelectronic feedback loops
Author(s) -
Yaping Chen,
Lilin Yi,
Junxiang Ke,
Zhao Yang,
Yunpeng Yang,
Luyao Huang,
Qunbi Zhuge,
Weisheng Hu
Publication year - 2019
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.27.027431
Subject(s) - reservoir computing , computer science , equalization (audio) , nonlinear system , popularity , convergence (economics) , channel (broadcasting) , feedback loop , optical computing , artificial neural network , electronic engineering , computer engineering , artificial intelligence , recurrent neural network , telecommunications , engineering , physics , psychology , social psychology , computer security , quantum mechanics , economics , economic growth
Reservoir computing (RC) by supervised training, a bio-inspired paradigm, is gaining popularity for processing time-dependent data. Compared to conventional recurrent neural networks, RC is facilely implemented by available hardware and overcomes some obstacles in training period, such as slow convergence and local optimum. In this paper, we propose and characterize a novel reservoir computing system based on a semiconductor laser with double optoelectronic feedback loops. This system shows obvious improvement on prediction, speech recognition and nonlinear channel equalization compared to the traditional reservoir computing systems with single feedback loop. Then some influencing factors to optimize the performance of the new RC are numerically studied, and its great potential of addressing more complex and troubling problems in information processing is expected to be exploited.