Low Complexity Convolutional Neural Networks for Equalization in Optical Fiber Transmission

10/11/2022

∙

A convolutional neural network is proposed to mitigate fiber transmission effects, achieving a five-fold reduction in trainable parameters compared to alternative equalizers, and 3.5 dB improvement in MSE compared to DBP with comparable complexity.

READ FULL TEXT

Low Complexity Convolutional Neural Networks for Equalization in Optical Fiber Transmission

Equalization in Dispersion-Managed Systems Using Learned Digital Back-Propagation

Bessel Equivariant Networks for Inversion of Transmission Effects in Multi-Mode Optical Fibres

Machine Learning for QoT Estimation of Unseen Optical Network States

Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices

Learning the Representations of Moist Convection with Convolutional Neural Networks

Low-complexity Approximate Convolutional Neural Networks

Smaller Models, Better Generalization

Low Complexity Convolutional Neural Networks for Equalization in Optical Fiber Transmission

Related Research

Equalization in Dispersion-Managed Systems Using Learned Digital Back-Propagation

Bessel Equivariant Networks for Inversion of Transmission Effects in Multi-Mode Optical Fibres

Machine Learning for QoT Estimation of Unseen Optical Network States

Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices

Learning the Representations of Moist Convection with Convolutional Neural Networks

Low-complexity Approximate Convolutional Neural Networks

Smaller Models, Better Generalization