Optical neural networks based on optical fiber-communication system

Tian You Cheng, Da Ya Chou, Ching Chuan Liu, Ya Ju Chang, Chii Chang Chen

研究成果: 雜誌貢獻期刊論文同行評審

22 引文 斯高帕斯(Scopus)

摘要

In this work, we propose a novel design for optical neural network system based on reservoir computing. The optical neurons in the system consist of directional couplers, optical fibers, and optical amplifiers. The nonlinear activation function of optical neuron can be obtained by the optical amplifiers. Mach–Zehnder phase modulators and the directional couplers are used to build the readout matrix in the output layer. The performance of the system is studied by a commercial software of optical fiber telecommunication system. The results show that the randomly connected optical neuron networks of the reservoir computing can provide a better performance.

原文???core.languages.en_GB???
頁(從 - 到)239-244
頁數6
期刊Neurocomputing
364
DOIs
出版狀態已出版 - 28 10月 2019

指紋

深入研究「Optical neural networks based on optical fiber-communication system」主題。共同形成了獨特的指紋。

引用此