• DOI:10.1109/spawc48557.2020.9154335
Corpus ID: 212415043

WGAN-based Autoencoder Training Over-the-air

@article{Drner2020WGANbasedAT,
  title={WGAN-based Autoencoder Training Over-the-air},
  author={Sebastian D{\"o}rner and Marcus Henninger and Sebastian Cammerer and S. Brink},
  journal={2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)},
  year={2020},
  pages={1-5}
}

• Sebastian Dörner, Marcus Henninger, +1 author S. Brink
• Published 2020
• Computer Science, Engineering, Mathematics
• 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

The practical realization of end-to-end training of communication systems is fundamentally limited by its accessibility of the channel gradient. To overcome this major burden, the idea of generative adversarial networks (GANs) that learn to mimic the actual channel behavior has been recently proposed in the literature. Contrarily to handcrafted classical channel modeling, which can never fully capture the real world, GANs promise, in principle, the ability to learn any physical impairment… Expand

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed