非线性傅立叶谱计算的神经网络

2021 European Conference on Optical Communication (ECOC) Pub Date : 2021-09-13 DOI:10.1109/ecoc52684.2021.9605844

E. Sedov, Pedro J. Freire, I. Chekhovskoy, S. Turitsyn, J. Prilepsky

{"title":"非线性傅立叶谱计算的神经网络","authors":"E. Sedov, Pedro J. Freire, I. Chekhovskoy, S. Turitsyn, J. Prilepsky","doi":"10.1109/ecoc52684.2021.9605844","DOIUrl":null,"url":null,"abstract":"We demonstrate that neural networks can outperform conventional numerical nonlinear Fourier transform algorithms for processing the noise-corrupted optical signal. Applying the Bayesian hyper-parameters optimisation, we design the architecture of neural networks capable to compute nonlinear signal spectrum at low SNR more accurately than conventional algorithms.","PeriodicalId":117375,"journal":{"name":"2021 European Conference on Optical Communication (ECOC)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Neural Networks For Nonlinear Fourier Spectrum Computation\",\"authors\":\"E. Sedov, Pedro J. Freire, I. Chekhovskoy, S. Turitsyn, J. Prilepsky\",\"doi\":\"10.1109/ecoc52684.2021.9605844\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We demonstrate that neural networks can outperform conventional numerical nonlinear Fourier transform algorithms for processing the noise-corrupted optical signal. Applying the Bayesian hyper-parameters optimisation, we design the architecture of neural networks capable to compute nonlinear signal spectrum at low SNR more accurately than conventional algorithms.\",\"PeriodicalId\":117375,\"journal\":{\"name\":\"2021 European Conference on Optical Communication (ECOC)\",\"volume\":\"110 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 European Conference on Optical Communication (ECOC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ecoc52684.2021.9605844\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 European Conference on Optical Communication (ECOC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ecoc52684.2021.9605844","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

我们证明了神经网络可以优于传统的数值非线性傅立叶变换算法来处理噪声损坏的光信号。应用贝叶斯超参数优化，我们设计的神经网络架构能够比传统算法更准确地计算低信噪比下的非线性信号频谱。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Neural Networks For Nonlinear Fourier Spectrum Computation

We demonstrate that neural networks can outperform conventional numerical nonlinear Fourier transform algorithms for processing the noise-corrupted optical signal. Applying the Bayesian hyper-parameters optimisation, we design the architecture of neural networks capable to compute nonlinear signal spectrum at low SNR more accurately than conventional algorithms.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2021 European Conference on Optical Communication (ECOC)

自引率

0.00%

发文量