Advertisement

Analysis of End-to-End Communication System Network Model

  • Kaiyao ZhangEmail author
  • Nan Wu
  • Xudong Wang
Conference paper
  • 576 Downloads
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 515)

Abstract

Deep learning has been very hot in the field of image recognition and natural language processing in recent years. In this article, we apply deep learning to the field of communication, using neural networks to build end-to-end communication systems under Gaussian channels, and jointly optimize the sender and receiver. The results show that the performance of the end-to-end communication system based on deep learning in Gaussian channel is better than the traditional communication system. Then we change the parameters and results of the network and analyze the results. Finally, we look forward to the next research direction.

Keywords

Autoencoder Communication system Deep learning Physical layer 

References

  1. 1.
    Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27, 379–423, 623–656 (1948)Google Scholar
  2. 2.
    Gagliardi, R.M., Karp, S.: Optical communications, 2nd edn. Wiley (1995)Google Scholar
  3. 3.
    Meyr, H., Moeneclaey, M., Fechtel, S.A.: Digital Communication Receivers: Synchronization, Channel Estimation, and Signal Processing. Wiley (1998)Google Scholar
  4. 4.
    Schenk, T.: RF imperfections in high-rate wireless systems: impact and digital compensation. Springer Science & Business Media (2008)Google Scholar
  5. 5.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)Google Scholar
  6. 6.
    O’Shea, T.J., Karra, K., Clancy, T.C.: Learning to communicate: Channel auto-encoders, domain specific regularizes, and attention. In: IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), pp. 223–228 (2016)Google Scholar
  7. 7.
    O’Shea, T.J., Hoydis, J.: An introduction to machine learning communications systems. arXiv preprint arXiv:1702.00832 (2017)
  8. 8.
    Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of AISTATS 2010, vol. 9, pp. 249–256Google Scholar
  9. 9.
    Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–127 (2009). (Also published as a book. Now Publishers)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Information Science and Technology College, Dalian Maritime UniversityDalianChina

Personalised recommendations