Revisiting Multi-Step Nonlinearity Compensation with Machine Learning

2019/04/22 by Häger, Christian, Pfister, Henry D., Bütler, Rick M. +2
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Information Theory (cs.IT) #Machine Learning (stat.ML) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1904.09807

Abstract

For the efficient compensation of fiber nonlinearity, one of the guiding principles appears to be: fewer steps are better and more efficient. We challenge this assumption and show that carefully designed multi-step approaches can lead to better performance-complexity trade-offs than their few-step counterparts.

Related

• Learning for Perturbation-Based Fiber Nonlinearity Compensation
• Tailored Shaping, Improved Detection, Simpler Backpropagation: the Road\n to Nonlinearity Mitigation
• Real-Time Machine Learning Based Fiber-Induced Nonlinearity Compensation\n in Energy-Efficient Coherent Optical Networks
• Deep Learning of the Nonlinear Schr "odinger Equation in Fiber-Optic\n Communications
• The Nonlinearity Coefficient - Predicting Generalization in Deep Neural Networks