Deep neural network-aided soft-demapping in coherent optical systems: Regression versus classification
We examine here what type of predictive modelling, classification, or regression, using
neural networks (NN), fits better the task of soft-demapping based post-processing in …
neural networks (NN), fits better the task of soft-demapping based post-processing in …
Complexity reduction over Bi-RNN-based nonlinearity mitigation in dual-pol fiber-optic communications via a CRNN-based approach
Bidirectional recurrent neural networks (bi-RNNs), in particular bidirectional long short term
memory (bi-LSTM), bidirectional gated recurrent unit, and convolutional bi-LSTM models …
memory (bi-LSTM), bidirectional gated recurrent unit, and convolutional bi-LSTM models …
Data-driven method for nonlinear optical fiber channel modeling based on deep neural network
R Jiang, Z Fu, Y Bao, H Wang, X Ding… - IEEE Photonics …, 2022 - ieeexplore.ieee.org
Recently, data-driven fiber channel modeling methods based on deep learning have been
proposed in optical communication system simulations. We investigate a new data-driven …
proposed in optical communication system simulations. We investigate a new data-driven …
Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization
The deployment of artificial neural networks-based optical channel equalizers on edge-
computing devices is critically important for the next generation of optical communication …
computing devices is critically important for the next generation of optical communication …
Parallelization of recurrent neural network-based equalizer for coherent optical systems via knowledge distillation
S Srivallapanondh, PJ Freire, B Spinnler… - Journal of Lightwave …, 2024 - opg.optica.org
The recurrent neural network (RNN)-based equalizers, especially the bidirectional long-
short-term memory (biLSTM) structure, have already been proven to outperform the feed …
short-term memory (biLSTM) structure, have already been proven to outperform the feed …
Efficient deep learning of kerr nonlinearity in fiber-optic channels using a convolutional recurrent neural network
A Shahkarami, MI Yousefi, Y Jaouen - Deep Learning Applications …, 2022 - Springer
The impairments arising from the Kerr nonlinearity in optical fiber are a major obstacle in
fiber-optic transmission systems. To compensate for these impairments at the receiver, the …
fiber-optic transmission systems. To compensate for these impairments at the receiver, the …
Deep convolutional recurrent neural network for fiber nonlinearity compensation
An iterative deep convolutional recurrent neural network is proposed to mitigate fiber
nonlinearity with distributed compensation of polarization mode dispersion, demonstrating …
nonlinearity with distributed compensation of polarization mode dispersion, demonstrating …
Deep neural network-aided soft-demapping in optical coherent systems: Regression versus classification
We examine here what type of predictive modelling, classification, or regression, using
neural networks (NN), fits better the task of soft-demapping based post-processing in …
neural networks (NN), fits better the task of soft-demapping based post-processing in …
Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization
The deployment of artificial neural networks-based optical channel equalizers on edge-
computing devices is critically important for the next generation of optical communication …
computing devices is critically important for the next generation of optical communication …
Self-supervised learning for neural-network-based perturbative fiber nonlinearity compensation
D Tang, Y Jiang, Z Wu, Y Qiao - 49th European Conference on …, 2023 - ieeexplore.ieee.org
A self-supervised learning scheme is proposed for neural-network-based perturbative fiber
nonlinearity compensation with a designed proxy task by using phase-conjugated unknown …
nonlinearity compensation with a designed proxy task by using phase-conjugated unknown …