Recurrent Neural Network based Equalizer with Embedded Parallelization for 100Gbps/λ PON
Xiaoan Huang, Dongxu Zhang, Xiaofeng Hu, Chenhui Ye, Kaibin Zhang
Abstract
Recurrent neural network based equalizer with parallel outputs is proposed and experimentally demonstrated. Result shows that it outperforms fully-connected neural network for 100Gbps/λ PON using 25G-class optics. Hardware implementation issues are also discussed.
Topics & Concepts
EqualizerComputer scienceArtificial neural networkRecurrent neural networkPassive optical networkClass (philosophy)BackpropagationParallel computingArtificial intelligenceComputer networkWavelength-division multiplexingOpticsWavelengthPhysicsChannel (broadcasting)Optical Network TechnologiesBlind Source Separation TechniquesSemiconductor Lasers and Optical Devices