Full-duplex (FD) systems have been introduced to provide high data rates forbeyond fifth-generation wireless networks . This article proposes two novel hybrid-layersneural network (NN) architectures to cancel the SI with low complexity . The key idea behindusing hybrid layers is to build an NN model, which makes use of the different layers employed in its architecture . In the HCRDNN, anadditional dense layer is exploited to add another degree of freedom foradapting the NN settings in order to achieve the best compromise between the performance and computational complexity . Complexity analysis andnumerical simulations are provided to prove the superiority of the proposedarchitectures . The first architecture is referred to as hybrid-convolutional recurrent NN (HCRNN), the second is termed as Hybrid-Convoutional recurrent dense NN(HCRDNN) The HCRCNN is called a hybrid-Convolutional Convolutional Recurrent NN architecture is used to extract the input data features using a reduced network scale. Morespecifically, in the H CRNN, a convolutional layer is employed to extract data features from a network scale using a low network scale to a low-cost network. In the

Author(s) : Mohamed Elsayed, Ahmad A. Aziz El-Banna, Octavia A. Dobre, Wanyi Shiu, Peiwei Wang

Links : PDF - Abstract

Code :
Coursera

Keywords : network - nn - hybrid - convolutional - layers -

Leave a Reply

Your email address will not be published. Required fields are marked *