Knowledge distillation applied to optical channel equalization: Solving the parallelization problem of recurrent connection
S Srivallapanondh, PJ Freire, B Spinnler… - Optical Fiber …, 2023 - opg.optica.org
Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization
Problem of Recurrent Connection Page 1 Knowledge Distillation Applied to Optical Channel …
Problem of Recurrent Connection Page 1 Knowledge Distillation Applied to Optical Channel …
Multi-task learning to enhance generazability of neural network equalizers in coherent optical systems
For the first time, multi-task learning is proposed to improve the flexibility of NN-based
equalizers in coherent systems. A" single" NN-based equalizer improves Q-factor by up to 4 …
equalizers in coherent systems. A" single" NN-based equalizer improves Q-factor by up to 4 …
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 …
Experimental study of deep neural network equalizers performance in optical links
PJ Freire, Y Osadchuk, B Spinnler… - 2021 Optical Fiber …, 2021 - ieeexplore.ieee.org
We propose a convolutional-recurrent channel equalizer and experimentally demonstrate
1dB Q-factor improvement both in single-channel and 96× WDM, DP-16QAM transmission …
1dB Q-factor improvement both in single-channel and 96× WDM, DP-16QAM transmission …
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 …
Domain adaptation: The key enabler of neural network equalizers in coherent optical systems
We introduce the domain adaptation and randomization approach for calibrating neural
network-based equalizers for real transmissions, using synthetic data. The approach …
network-based equalizers for real transmissions, using synthetic data. The approach …
Feedforward and recurrent neural network-based transfer learning for nonlinear equalization in short-reach optical links
Neural network (NN)-based nonlinear equalizers have been shown effective for various
types of short-reach direct detection systems. However, they work best for a certain channel …
types of short-reach direct detection systems. However, they work best for a certain channel …
Transfer learning for neural networks-based equalizers in coherent optical systems
In this work, we address the question of the adaptability of artificial neural networks (NNs)
used for impairments mitigation in optical transmission systems. We demonstrate that by …
used for impairments mitigation in optical transmission systems. We demonstrate that by …
Performance versus complexity study of neural network equalizers in coherent optical systems
We present the results of the comparative performance-versus-complexity analysis for the
several types of artificial neural networks (NNs) used for nonlinear channel equalization in …
several types of artificial neural networks (NNs) used for nonlinear channel equalization in …
Attention-based neural network equalization in fiber-optic communications
A Shahkarami, MI Yousefi, Y Jaouën - Asia Communications and …, 2021 - opg.optica.org
Attention-Based Neural Network Equalization in Fiber-Optic Communications Page 1
Attention-Based Neural Network Equalization in Fiber-Optic Communications Abtin …
Attention-Based Neural Network Equalization in Fiber-Optic Communications Abtin …