Nonlinear Interference Mitigation via Deep Neural Networks

10/17/2017

∙

A neural-network-based approach is presented to efficiently implement digital backpropagation (DBP). For a 32x100 km fiber-optic link, the resulting "learned" DBP significantly reduces the complexity compared to conventional DBP implementations.

READ FULL TEXT

Nonlinear Interference Mitigation via Deep Neural Networks

ASIC Implementation of Time-Domain Digital Backpropagation with Deep-Learned Chromatic Dispersion Filters

Coherent 100G Nonlinear Compensation with Single-Step Digital Backpropagation

Compressing Low Precision Deep Neural Networks Using Sparsity-Induced Regularization in Ternary Networks

Leapfrogging for parallelism in deep neural networks

Tailored Shaping, Improved Detection, Simpler Backpropagation: the Road to Nonlinearity Mitigation

Hardware Implementation of Neural Self-Interference Cancellation

Deep Neural Network Based Subspace Learning of Robotic Manipulator Workspace Mapping

Nonlinear Interference Mitigation via Deep Neural Networks

Related Research

ASIC Implementation of Time-Domain Digital Backpropagation with Deep-Learned Chromatic Dispersion Filters

Coherent 100G Nonlinear Compensation with Single-Step Digital Backpropagation

Compressing Low Precision Deep Neural Networks Using Sparsity-Induced Regularization in Ternary Networks

Leapfrogging for parallelism in deep neural networks

Tailored Shaping, Improved Detection, Simpler Backpropagation: the Road to Nonlinearity Mitigation

Hardware Implementation of Neural Self-Interference Cancellation

Deep Neural Network Based Subspace Learning of Robotic Manipulator Workspace Mapping