期刊
OPTICAL MATERIALS EXPRESS
卷 12, 期 3, 页码 1140-1153出版社
OPTICAL SOC AMER
DOI: 10.1364/OME.450256
关键词
-
Reservoir computing is a machine learning approach that allows the use of recurrent neural networks without the complexity of training algorithms and enables hardware implementation. Researchers present a novel photonic architecture for a reservoir computer using a nonlinear node and a resonator to implement a virtual recurrent neural network. The performance of the proposed reservoir is tested on three benchmark tasks and shows improved memory capacity and reliable results compared to delay-based systems.
Reservoir computing is a machine learning approach that enables us to use recurrent neural networks without involving the complexity of training algorithms and make hardware implementation possible. We present a novel photonic architecture of a reservoir computer that employs a nonlinear node and a resonator to implement a virtual recurrent neural network. This resonator behaves as an echo generator component that substitutes the delay line in delay-based reservoir computers available in the literature. The virtual neural network formed in our implementation is fundamentally different from the delay-based reservoir computers. Different virtual architectures based on the FSR and the Finesse of the resonator are investigated to provide higher performance depending on the task. We test the performance of our proposed reservoir by 3 benchmark tasks, signal classification, nonlinear channel equalization, and memory capacity. Our system enhances the memory capacity of the reservoir compared to the delay-based systems and shows reliable results in signal classification and nonlinear channel equalization. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据