Residual-Aided End-to-End Learning of Communication System Without Known Channel

Residual-Aided End-to-End Learning of Communication System Without Known Channel

Leveraging powerful deep learning techniques, the end-to-end (E2E) learning of communication system is able to outperform the classical communication system. Unfortunately, this communication system cannot be trained by deep learning without known channel. To deal with this problem, a generative adv...

Full description

Bibliographic Details
Main Authors: Bi, S. (Author), Dai, L. (Author), Jiang, H. (Author), Wang, H. (Author), Zhang, J. (Author)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2022
Subjects:
Backpropagation
Communication channels (information theory)
Communications systems
Deep learning
End to end
End-to-end learning
Generative adversarial network
generative adversarial network (GAN)
Generative adversarial networks
Network-based
Neural-networks
Over fitting problem
Ray tracing
Regularisation
regularization
residual neural network
Residual neural network
Training schemes
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items