Artificial neural networks for photonic applications—from algorithms to implementation: tutorial

P Freire, E Manuylovich, JE Prilepsky… - Advances in Optics and …, 2023 - opg.optica.org
This tutorial–review on applications of artificial neural networks in photonics targets a broad
audience, ranging from optical research and engineering communities to computer science …

Neural networks-based equalizers for coherent optical transmission: Caveats and pitfalls

PJ Freire, A Napoli, B Spinnler, N Costa… - IEEE Journal of …, 2022 - ieeexplore.ieee.org
This paper performs a detailed, multi-faceted analysis of key challenges and common
design caveats related to the development of efficient neural networks (NN) based nonlinear …

Recurrent Neural Networks and Recurrent Optical Spectrum Slicers as Equalizers in High Symbol Rate Optical Transmission Systems

K Sozos, S Deligiannidis, G Sarantoglou… - Journal of Lightwave …, 2023 - ieeexplore.ieee.org
The transition to the edge-cloud era makes ultra-high data rate signals indispensable for
covering the immense and increasing traffic demands created. This ecosystem also seeks …

Neural network-aided receivers for soliton communication impaired by solitonic interaction

Y Chen, M Baniasadi, M Safari - Optics Express, 2023 - opg.optica.org
In this paper, different neural network-based methods are proposed to improve the
achievable information rate in amplitude-modulated soliton communication systems. The …

Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization

DA Ron, PJ Freire, JE Prilepsky, M Kamalian-Kopae… - Scientific Reports, 2022 - nature.com
The deployment of artificial neural networks-based optical channel equalizers on edge-
computing devices is critically important for the next generation of optical communication …

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

Y Liu, V Sanchez, PJ Freire, JE Prilepsky… - Optics …, 2022 - opg.optica.org
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 …

Blind channel equalization using vector-quantized variational autoencoders

J Song, V Lauinger, Y Wu, C Häger, J Schröder… - arXiv preprint arXiv …, 2023 - arxiv.org
State-of-the-art high-spectral-efficiency communication systems employ high-order
modulation formats coupled with high symbol rates to accommodate the ever-growing …

Gesture Classification in Electromyography Signals for Real-Time Prosthetic Hand Control Using a Convolutional Neural Network-Enhanced Channel Attention Model

G Yu, Z Deng, Z Bao, Y Zhang, B He - Bioengineering, 2023 - mdpi.com
Accurate and real-time gesture recognition is required for the autonomous operation of
prosthetic hand devices. This study employs a convolutional neural network-enhanced …

A Data-Driven Digital Demodulator Based on Deep Learning for Radio Over Fiber Transmission System

Y Zhu, J Ye, L Yan, T Zhou, X Yu, P Li… - Journal of Lightwave …, 2023 - ieeexplore.ieee.org
A data-driven digital demodulator based on a Fourier layer Transformer network (FTnet) for
radio over fiber (RoF) transmission system with quadrature amplitude modulation (QAM) is …

Finite-Genus Solutions-based Optical Communication with the Riemann-Hilbert Problem Transmitter and a Convolutional Neural Network Receiver

S Bogdanov, D Shepelsky… - Journal of Lightwave …, 2024 - ieeexplore.ieee.org
In the study, we develop a new optical communication system based on the nonlinear
Fourier transform for generic (quasiperiodic) finite-genus solutions to the nonlinear …