Abstract | ||
---|---|---|
Hybrid beamforming is integral to massive multiple-input multiple-output (MIMO) communications in reducing the training overhead and hardware cost associated with large antenna arrays. Prior works have employed optimization and greedy search to jointly estimate the precoder and combiner weights. High computational complexity of these methods apart, their performance strongly relies on accurate channel information. In this paper, we propose a computationally efficient, deep learning approach that also provides robust performance against the deviations in the channel characteristics. Further, we employ a convolutional neural network with quantized weights (Q-CNN) so that it is deployable in mobile devices that have less memory resources and low overhead requirements. We show that the proposed Q-CNN, saved in at least 6 bits, yields superior performance over conventional massive MIMO hybrid beamforming. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/MLSP.2019.8918866 | 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP) |
Keywords | Field | DocType |
Convolutional neural networks,deep learning,hybrid beamforming,massive MIMO,quantization | Baseband,Pattern recognition,Computer science,Convolutional neural network,MIMO,Communication channel,Greedy algorithm,Robustness (computer science),Artificial intelligence,Deep learning,Computer engineering,Computational complexity theory | Conference |
ISSN | ISBN | Citations |
1551-2541 | 978-1-7281-0825-4 | 0 |
PageRank | References | Authors |
0.34 | 16 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ahmet M. Elbir | 1 | 91 | 11.29 |
Kumar Vijay Mishra | 2 | 164 | 19.95 |