English

Over-the-fiber Digital Predistortion Using Reinforcement Learning

Signal Processing 2021-06-10 v1
Authors: Jinxiang Song , Zonglong He , Christian Häger , Magnus Karlsson , Alexandre Graell i Amat , Henk Wymeersch , Jochen Schröder
View on arXiv ↗ PDF ↗

Abstract

We demonstrate, for the first time, experimental over-the-fiber training of transmitter neural networks (NNs) using reinforcement learning. Optical back-to-back training of a novel NN-based digital predistorter outperforms arcsine-based predistortion with up to 60\% bit-error-rate reduction.

Keywords

neural networks for signal processing

Cite

@article{arxiv.2106.04934,
  title  = {Over-the-fiber Digital Predistortion Using Reinforcement Learning},
  author = {Jinxiang Song and Zonglong He and Christian Häger and Magnus Karlsson and Alexandre Graell i Amat and Henk Wymeersch and Jochen Schröder},
  journal= {arXiv preprint arXiv:2106.04934},
  year   = {2021}
}

Related papers

View all related →
Signal Processing · Electrical Eng. & Systems
Design and Implementation of a Neural Network Based Predistorter for Enhanced Mobile Broadband
Chance Tarver, Alexios Balatsoukas-Stimming, Joseph R. Cavallaro
2019-07-02
Signal Processing · Electrical Eng. & Systems
Symbol-Based Over-the-Air Digital Predistortion Using Reinforcement Learning
Yibo Wu, Jinxiang Song, Christian Häger, Ulf Gustavsson +2
2021-11-24
Machine Learning · Computer Science
Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks
Sina Ghiassian, Banafsheh Rafiee, Yat Long Lo, Adam White
2020-03-18
Signal Processing · Electrical Eng. & Systems
Efficient Training of Volterra Series-Based Pre-distortion Filter Using Neural Networks
Vinod Bajaj, Mathieu Chagnon, Sander Wahls, Vahid Aref
2021-12-14
Signal Processing · Electrical Eng. & Systems
Training of mixed-signal optical convolutional neural network with reduced quantization level
Joseph Ulseth, Zheyuan Zhu, Guifang Li, Shuo Pang
2021-07-01
Signal Processing · Electrical Eng. & Systems
Residual Neural Networks for Digital Predistortion
Yibo Wu, Ulf Gustavsson, Alexandre Graell i Amat, Henk Wymeersch
2020-10-20
Computer Vision and Pattern Recognition · Computer Science
Training on Foveated Images Improves Robustness to Adversarial Attacks
Muhammad A. Shah, Bhiksha Raj
2023-08-03
Machine Learning · Computer Science
Forward-Forward Training of an Optical Neural Network
Ilker Oguz, Junjie Ke, Qifei Wang, Feng Yang +5
2023-08-11
Emerging Technologies · Computer Science
Transferable Learning on Analog Hardware
Sri Krishna Vadlamani, Dirk Englund, Ryan Hamerly
2022-10-14
Neural and Evolutionary Computing · Computer Science
Training large-scale ANNs on simulated resistive crossbar arrays
Malte J. Rasch, Tayfun Gokmen, Wilfried Haensch
2023-02-17
Computer Vision and Pattern Recognition · Computer Science
Unsupervised Learning for Large-Scale Fiber Detection and Tracking in Microscopic Material Images
Hongkai Yu, Dazhou Guo, Zhipeng Yan, Wei Liu +3
2018-05-28
Machine Learning · Computer Science
Overcoming the Spectral Bias of Neural Value Approximation
Ge Yang, Anurag Ajay, Pulkit Agrawal
2022-06-10
Signal Processing · Electrical Eng. & Systems
Adversarial Training: Enhancing Out-of-Distribution Generalization for Learning Wireless Resource Allocation
Shengjie Liu, Chenyang Yang
2026-03-03
Disordered Systems and Neural Networks · Physics
Reconstructing signal from fiber-optic measuring system with non-linear perceptron
A. V. Panov
2007-05-23
Machine Learning · Computer Science
Training Adaptive Reconstruction Networks for Blind Inverse Problems
Alban Gossard, Pierre Weiss
2023-12-19
Optics · Physics
Learning to see through multimode fibers
Navid Borhani, Eirini Kakkava, Christophe Moser, Demetri Psaltis
2018-08-21
Signal Processing · Electrical Eng. & Systems
Optical Fiber Communication Systems Based on End-to-End Deep Learning
Boris Karanov, Mathieu Chagnon, Vahid Aref, Domanic Lavery +2
2020-05-19
Neural and Evolutionary Computing · Computer Science
Reinforcement Learning in a large scale photonic Recurrent Neural Network
Julian Bueno, Sheler Maktoobi, Luc Froehly, Ingo Fischer +3
2019-05-13
Cryptography and Security · Computer Science
Optimizing Information Loss Towards Robust Neural Networks
Philip Sperl, Konstantin Böttinger
2020-09-30
Machine Learning · Computer Science
Resilient Binary Neural Network
Sheng Xu, Yanjing Li, Teli Ma, Mingbao Lin +4
2023-02-07
Networking and Internet Architecture · Computer Science
Optimizing Reinforcement Learning Training over Digital Twin Enabled Multi-fidelity Networks
Hanzhi Yu, Hasan Farooq, Julien Forgeat, Shruti Bothe +3
2026-03-11
Machine Learning · Computer Science
Achieving Generalizable Robustness of Deep Neural Networks by Stability Training
Jan Laermann, Wojciech Samek, Nils Strodthoff
2019-11-14
Signal Processing · Electrical Eng. & Systems
Experimental Demonstration of Millimeter-Wave Radio-over-Fiber System with Convolutional Neural Network (CNN) and Binary Convolutional Neural Network (BCNN)
Jeonghun Lee, Jiayuan He, Yitong Wang, Chengwei Fang +1
2020-01-08
Machine Learning · Computer Science
Efficient Training Convolutional Neural Networks on Edge Devices with Gradient-pruned Sign-symmetric Feedback Alignment
Ziyang Hong, C. Patrick Yue
2021-05-14
Emerging Technologies · Computer Science
Efficient On-Chip Learning for Optical Neural Networks Through Power-Aware Sparse Zeroth-Order Optimization
Jiaqi Gu, Chenghao Feng, Zheng Zhao, Zhoufeng Ying +2
2021-09-07
R2 v1 2026-06-24T02:59:46.277Z