International Journal of Microwave and Wireless Technologies · 2021 · 25 citations · 16 references
EngineeringComputer EngineeringElectrical EngineeringAntennasComputational ElectromagneticsWireless CommunicationsAntenna ArraysAntenna DesignBeam SteeringBeamformingDeep LearningSmart AntennasAdaptive BeamformingComputational Complexity Of AlgorithmsConvolutional Neural NetworksNeural Network ModelingPhased Array AntennasPhased Array BeamformingRadial Basis Function NetworksRobust Beamforming
Abstract Achieving robust and fast two-dimensional adaptive beamforming of phased array antennas is a challenging problem due to its high-computational complexity. To address this problem, a deep-learning-based beamforming method is presented in this paper. In particular, the optimum weight vector is computed by modeling the problem as a convolutional neural network (CNN), which is trained with I/O pairs obtained from the optimum Wiener solution. In order to exhibit the robustness of the new technique, it is applied on an 8 × 8 phased array antenna and compared with a shallow (non-deep) neural network namely, radial basis function neural network. The results reveal that the CNN leads to nearly optimal Wiener weights even in the presence of array imperfections.
16
A Light CNN for Deep Face Representation With Noisy Labels
Xiang Wu, Ran He, Zhenan Sun et al. · IEEE Transactions on Information Forensics and Security · 2018 · 1.2K citations
Huan Xu, Shie Mannor · Machine Learning · 2011 · 373 citations · Full text