Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
  • Journal of Lightwave Technology
  • Vol. 39,
  • Issue 20,
  • pp. 6381-6391
  • (2021)

Gradient-Free Training of Autoencoders for Non-Differentiable Communication Channels

Not Accessible

Your library or personal account may give you access

Abstract

Training of autoencoders using the back-propagation algorithm is challenging for non-differential channel models or in an experimental environment where gradients cannot be computed. In this paper, we study a gradient–free training method based on the cubature Kalman filter. To numerically validate the method, the autoencoder is employed to perform geometric constellation shaping on differentiable communication channels, showing the same performance as the back-propagation algorithm. Further investigation is done on a non–differentiable communication channel that includes: laser phase noise, additive white Gaussian noise and blind phase search-based phase noise compensation. Our results indicate that the autoencoder can be successfully optimized using the proposed training method to achieve better robustness to residual phase noise with respect to standard constellation schemes such as Quadrature Amplitude Modulation and Iterative Polar Modulation for the considered conditions.

PDF Article
More Like This
Initialized autoencoders to find constellations robust to residual laser phase noise

Amir Omidi, Xun Guan, Ming Zeng, and Leslie A. Rusch
Opt. Continuum 2(6) 1384-1400 (2023)

Attention-assisted autoencoder neural network for end-to-end optimization of multi-access fiber-terahertz communication systems

Zhongya Li, Boyu Dong, Guoqiang Li, Junlian Jia, Aolong Sun, Wangwei Shen, Sizhe Xing, Jianyang Shi, Nan Chi, and Junwen Zhang
J. Opt. Commun. Netw. 15(9) 711-725 (2023)

One-bit quantization delta-sigma modulation-based autoencoder for power-efficient free-space communication

Jifan Cai, Zhilan Lu, Zhiteng Luo, Junwen Zhang, and Nan Chi
Opt. Lett. 48(20) 5217-5220 (2023)

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.