Neural Network Equalizers and Successive Interference Cancellation for Bandlimited Channels with a Nonlinearity
Daniel Plabst, Tobias Prinz, Francesca Diedolo, Thomas Wiegart, Technical University of Munich, Germany; Georg Böcherer, Huawei Technologies Düsseldorf GmbH, Germany; Norbert Hanik, Gerhard Kramer, Technical University of Munich, Germany
Session:
Student Paper Award 1
Track:
21: Other topics
Location:
Ballroom II & III
Presentation Time:
Mon, 8 Jul, 10:45 - 11:05
Session Chair:
Sueli Irene Rodriguez Costa,
Abstract
Neural networks (NNs) inspired by the forward-backward algorithm (FBA) are used as equalizers for bandlimited channels with a memoryless nonlinearity. The NN-equalizers are combined with successive interference cancellation (SIC) to approach the information rates of joint detection and decoding (JDD) with considerably less complexity than JDD and other existing equalizers. Simulations for short-haul optical fiber links with square-law detection illustrate the gains.