Attention-aided partial bidirectional RNN-based nonlinear equalizer in coherent optical systems.

We leverage the attention mechanism to investigate and comprehend the contribution of each input symbol of the input sequence and their hidden representations for predicting the received symbol in the bidirectional recurrent neural network (BRNN)-based nonlinear equalizer. In this paper, we propose an attention-aided novel design of a partial BRNN-based nonlinear equalizer, and evaluate with both LSTM and GRU units in a single-channel DP-64QAM 30Gbaud coherent optical communication systems of 20 × 50 km standard single-mode fiber (SSMF) spans. Our approach maintains the Q-factor performance of the baseline equalizer with a significant complexity reduction of ∼56.16% in the number of real multiplications required to equalize per symbol (RMpS). In comparison of the performance under similar complexity, our approach outperforms the baseline by ∼0.2dB to ∼0.25dB at the optimal transmit power, and ∼0.3dB to ∼0.45dB towards the more nonlinear region.

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 systems. However, this is still a highly challenging problem, mainly due to the computational complexity of the artificial neural networks (NNs) required for the efficient equalization of nonlinear optical channels with large dispersion-induced memory. To implement the NN-based optical channel equalizer in hardware, a substantial complexity reduction is needed, while we have to keep an acceptable performance level of the simplified NN model. In this work, we address the complexity reduction problem by applying pruning and quantization techniques to an NN-based optical channel equalizer. We use an exemplary NN architecture, the multi-layer perceptron (MLP), to mitigate the impairments for 30 GBd 1000 km transmission over a standard single-mode fiber, and demonstrate that it is feasible to reduce the equalizer's memory by up to 87.12%, and its complexity by up to 78.34%, without noticeable performance degradation. In addition to this, we accurately define the computational complexity of a compressed NN-based equalizer in the digital signal processing (DSP) sense. Further, we examine the impact of using hardware with different CPU and GPU features on the power consumption and latency for the compressed equalizer. We also verify the developed technique experimentally, by implementing the reduced NN equalizer on two standard edge-computing hardware units: Raspberry Pi 4 and Nvidia Jetson Nano, which are used to process the data generated via simulating the signal's propagation down the optical-fiber system.

Neural networks for computing and denoising the continuous nonlinear Fourier spectrum in focusing nonlinear Schrödinger equation.

We combine the nonlinear Fourier transform (NFT) signal processing with machine learning methods for solving the direct spectral problem associated with the nonlinear Schrödinger equation. The latter is one of the core nonlinear science models emerging in a range of applications. Our focus is on the unexplored problem of computing the continuous nonlinear Fourier spectrum associated with decaying profiles, using a specially-structured deep neural network which we coined NFT-Net. The Bayesian optimisation is utilised to find the optimal neural network architecture. The benefits of using the NFT-Net as compared to the conventional numerical NFT methods becomes evident when we deal with noise-corrupted signals, where the neural networks-based processing results in effective noise suppression. This advantage becomes more pronounced when the noise level is sufficiently high, and we train the neural network on the noise-corrupted field profiles. The maximum restoration quality corresponds to the case where the signal-to-noise ratio of the training data coincides with that of the validation signals. Finally, we also demonstrate that the NFT b-coefficient important for optical communication applications can be recovered with high accuracy and denoised by the neural network with the same architecture.