AdaNN: Adaptive Neural Network-Based Equalizer via Online Semi-Supervised Learning

  title={AdaNN: Adaptive Neural Network-Based Equalizer via Online Semi-Supervised Learning},
  author={Qingyi Zhou and F. Zhang and Chuanchuan Yang},
  journal={Journal of Lightwave Technology},
The demand for high speed data transmission has increased rapidly over the past few years, leading to the development of advanced optical communication techniques. [...] Key Method The online training scheme originates from decision-directed adaptive equalization. By combining it with data augmentation and virtual adversarial training, we've successfully increased the convergence speed by 4.5 times. The proposed adaptive NN-based equalizer is called "AdaNN". Its BER has been evaluated over a 56 Gb/s PAM4…Expand
4 Citations
Design of Amended Adaptive Equalizer using Butterfly Optimization Algorithm : Extension to LTE System
  • Highly Influenced
Long Short-Term Memory Neuron Equalizer.
  • PDF
Large-Scale High-Density Optical Interconnects
  • Z. Chen, Chuanchuan Yang, +5 authors S. Huang
  • 2020 Asia Communications and Photonics Conference (ACP) and International Conference on Information Photonics and Optical Communications (IPOC)
  • 2020


Online Label Recovery for Deep Learning-based Communication through Error Correcting Codes
  • 18
  • PDF
Backpropagating Through the Air: Deep Learning at Physical Layer Without Channel Models
  • 46
Deep Learning Based on Orthogonal Approximate Message Passing for CP-Free OFDM
  • 8
  • PDF
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
  • 840
  • Highly Influential
  • PDF
An Introduction to Deep Learning for the Physical Layer
  • T. O'Shea, J. Hoydis
  • Computer Science, Mathematics
  • IEEE Transactions on Cognitive Communications and Networking
  • 2017
  • 913
  • PDF
Deep Learning-Based Channel Estimation for High-Dimensional Signals
  • 13
  • PDF
Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems
  • H. Ye, G. Li, B. Juang
  • Computer Science, Mathematics
  • IEEE Wireless Communications Letters
  • 2018
  • 552
  • PDF
Temporal Ensembling for Semi-Supervised Learning
  • 644
  • PDF