… MIMO-OFDM symbol detection strategies focusing on a special recurrent neural network (RNN)
– … In this paper, we focus on the problem of symbol detection in MIMO-OFDM which is the …

… Abstract—This paper proposes to use a deep neural network (DNN)-based symbol
detector for … In particular, we consider a sliding bidirectional recurrent neural network (BRNN) …

… This paper introduced a deep RNN-based network called RCNet to 1) … -based symbol
detection strategies to further improve the detection performance of RC-based symbol detectors. …

… This paper explores deep learning (DL), specifically by using a proposed architecture … -RNN
hybrid model to perform symbol detection on BFSK, QPSK and 16-QAM. The CNN-RNN …

… The combination of RNN dynamics and the time-frequency structure of MIMO-OFDM … symbol
detection is essentially a classification problem, we can utilize NNs for symbol detection via …

… of BLSTM RNN used for online symbol classification task and our … Maxout function groups
the linear activations in detection layer … Layers can be stacked on each other to form deeper …

… For comparison, we numerically compute the SER of the Viterbi algorithm, as well as that
of the sliding bidirectional RNN (SBRNN) deep symbol decoder proposed in [15]. In order to …

… Our proposed RNN model to symbol detection involves a Bi-LSTM model. Here, we set
the minibatch size to 1000, learning rate to 0.001, the number of epochs to 100, and choose …

… One of the most common symbol detection schemes is the Viterbi algorithm, which is capable
of … symbol detector obtained by converting the Viterbi algorithm into a system utilizing deep …

… Similarly, the cells of the RNN-B also accept the received symbol sequence and process the
… : With respect to sequence detection, we use RNN, BRNN, and SBRNN as benchmarks and …