A Fiber Nonlinearity Compensation Scheme With Complex-Valued Dimension-Reduced Neural Network
A fiber nonlinearity compensation scheme based on a complex-valued dimension-reduced neural network is proposed. The proposed scheme performs all calculations in complex values and employs a dimension-reduced triplet feature vector to reduce the size of the input layer. Simulation and experiment res...
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IEEE
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/090cfc81acd9481497ed8b2dfbecfad7 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:090cfc81acd9481497ed8b2dfbecfad7 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:090cfc81acd9481497ed8b2dfbecfad72021-11-18T00:00:11ZA Fiber Nonlinearity Compensation Scheme With Complex-Valued Dimension-Reduced Neural Network1943-065510.1109/JPHOT.2021.3123624https://doaj.org/article/090cfc81acd9481497ed8b2dfbecfad72021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9594671/https://doaj.org/toc/1943-0655A fiber nonlinearity compensation scheme based on a complex-valued dimension-reduced neural network is proposed. The proposed scheme performs all calculations in complex values and employs a dimension-reduced triplet feature vector to reduce the size of the input layer. Simulation and experiment results show that the proposed neural network needed only 20% of computational complexity to reach the saturated performance gain of the real-valued triplet-input neural network, and had a similar saturated gain to the one-step-per-span digital backpropagation. In addition, the proposed scheme was 1.7 dB more robust to the noise from training data and required less bit precision for quantizing trained weights, compared with the real-valued triplet-input neural network.Pinjing HeFeilong WuMeng YangAiying YangPeng GuoYaojun QiaoXiangjun XinIEEEarticleKerr effectfiber nonlinearity compensationneural networkApplied optics. PhotonicsTA1501-1820Optics. LightQC350-467ENIEEE Photonics Journal, Vol 13, Iss 6, Pp 1-7 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Kerr effect fiber nonlinearity compensation neural network Applied optics. Photonics TA1501-1820 Optics. Light QC350-467 |
| spellingShingle |
Kerr effect fiber nonlinearity compensation neural network Applied optics. Photonics TA1501-1820 Optics. Light QC350-467 Pinjing He Feilong Wu Meng Yang Aiying Yang Peng Guo Yaojun Qiao Xiangjun Xin A Fiber Nonlinearity Compensation Scheme With Complex-Valued Dimension-Reduced Neural Network |
| description |
A fiber nonlinearity compensation scheme based on a complex-valued dimension-reduced neural network is proposed. The proposed scheme performs all calculations in complex values and employs a dimension-reduced triplet feature vector to reduce the size of the input layer. Simulation and experiment results show that the proposed neural network needed only 20% of computational complexity to reach the saturated performance gain of the real-valued triplet-input neural network, and had a similar saturated gain to the one-step-per-span digital backpropagation. In addition, the proposed scheme was 1.7 dB more robust to the noise from training data and required less bit precision for quantizing trained weights, compared with the real-valued triplet-input neural network. |
| format |
article |
| author |
Pinjing He Feilong Wu Meng Yang Aiying Yang Peng Guo Yaojun Qiao Xiangjun Xin |
| author_facet |
Pinjing He Feilong Wu Meng Yang Aiying Yang Peng Guo Yaojun Qiao Xiangjun Xin |
| author_sort |
Pinjing He |
| title |
A Fiber Nonlinearity Compensation Scheme With Complex-Valued Dimension-Reduced Neural Network |
| title_short |
A Fiber Nonlinearity Compensation Scheme With Complex-Valued Dimension-Reduced Neural Network |
| title_full |
A Fiber Nonlinearity Compensation Scheme With Complex-Valued Dimension-Reduced Neural Network |
| title_fullStr |
A Fiber Nonlinearity Compensation Scheme With Complex-Valued Dimension-Reduced Neural Network |
| title_full_unstemmed |
A Fiber Nonlinearity Compensation Scheme With Complex-Valued Dimension-Reduced Neural Network |
| title_sort |
fiber nonlinearity compensation scheme with complex-valued dimension-reduced neural network |
| publisher |
IEEE |
| publishDate |
2021 |
| url |
https://doaj.org/article/090cfc81acd9481497ed8b2dfbecfad7 |
| work_keys_str_mv |
AT pinjinghe afibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT feilongwu afibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT mengyang afibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT aiyingyang afibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT pengguo afibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT yaojunqiao afibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT xiangjunxin afibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT pinjinghe fibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT feilongwu fibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT mengyang fibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT aiyingyang fibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT pengguo fibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT yaojunqiao fibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork AT xiangjunxin fibernonlinearitycompensationschemewithcomplexvalueddimensionreducedneuralnetwork |
| _version_ |
1718425266991136768 |