Application of complex-valued convolutional neural network for next generation wireless networks

@article{Marseet2017ApplicationOC,
  title={Application of complex-valued convolutional neural network for next generation wireless networks},
  author={Akram Marseet and Ferat Sahin},
  journal={2017 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)},
  year={2017},
  pages={1-5}
}
A novel Complex-Valued Convolutional Neural Network (CV-CNN) model is proposed for the detection process in Multiple Input Multiple Output next generation wireless networks. The proposed model is used a as an auto-encoder based CV-CNN which is based on using the absolute value as the activation function and the L1-Norm as the loss function instead of the Euclidean norm. The proposed model is used for the joint detection of the index of the transmitted symbols and the index of the spatial… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

A novel stacked denoising autoencoder with swarm intelligence optimization for stock index prediction

  • 2017 International Joint Conference on Neural Networks (IJCNN)
  • 2017
VIEW 1 EXCERPT

An Introduction to Deep Learning for the Physical Layer

Oshea, Tim, Hoydis, Jakob
  • IEEE Transactions on Cognitive Communications and Networking
  • 2017
VIEW 3 EXCERPTS

An investigation of energy efficiency in 5G wireless networks

  • 2017 International Conference on Circuits, System and Simulation (ICCSS)
  • 2017
VIEW 1 EXCERPT

Development of active phased array antenna for high SHF wideband massive MIMO in 5G

  • 2017 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting
  • 2017
VIEW 2 EXCERPTS

Massive MIMO approach for interference reduction using precoding

  • 2017 International Conference on Smart, Monitored and Controlled Cities (SM2C)
  • 2017
VIEW 2 EXCERPTS

On optimal training in massive MIMO systems with insufficient pilots

  • 2017 IEEE International Conference on Communications (ICC)
  • 2017
VIEW 1 EXCERPT