Deep LearningBased Constellation Optimization for Physical Network Coding in TwoWay Relay Networks
Abstract
This paper studies a new application of deep learning (DL) for optimizing constellations in twoway relaying with physicallayer network coding (PNC), where deep neural network (DNN)based modulation and demodulation are employed at each terminal and relay node. We train DNNs such that the cross entropy loss is directly minimized, and thus it maximizes the likelihood, rather than considering the Euclidean distance of the constellations. The proposed scheme can be extended to higher level constellations with slight modification of the DNN structure. Simulation results demonstrate a significant performance gain in terms of the achievable sum rate over conventional relaying schemes. Furthermore, since our DNN demodulator directly outputs bitwise probabilities, it is straightforward to concatenate with softdecision channel decoding.
 Publication:

arXiv eprints
 Pub Date:
 March 2019
 arXiv:
 arXiv:1903.03713
 Bibcode:
 2019arXiv190303713M
 Keywords:

 Computer Science  Information Theory;
 Computer Science  Machine Learning;
 Electrical Engineering and Systems Science  Signal Processing;
 Statistics  Machine Learning