A Model-Driven Deep Learning Method for Normalized Min-Sum LDPC Decoding

A Review of Deep Learning in 5G Research: Channel Coding, Massive MIMO, Multiple Access, Resource Allocation, and Network Security

“…Since 5G communications systems have adopted polar codes, specifically LDPC codes, DL has been used to discover methods to blindly identify LDPC codes [23], reduce the decoding delay [25], [36], [37], [38], analyze the trade-off of LDPC codes for channel coding [24], develop error correction codes for nonlinear channels [39] and optimize the decoding algorithm to solve a non-convex minimization problem [40]. As expected, when comparing traditional decoding to DL-based decoding, DL has a greater reward.…”

“…Literature [37] and [38], unlike [25] and [36], utilizes a lowcomplexity BP-based decoding method. [37] relies on its early stopping prediction stage and decodability detection stage to eliminate the unnecessary decoding operations that increase the complexity of LDPC decoding for polar codes; it successfully achieves a 71% decoding delay reduction while maintaining the same decoding performance as traditional schemes.…”

“…[37] relies on its early stopping prediction stage and decodability detection stage to eliminate the unnecessary decoding operations that increase the complexity of LDPC decoding for polar codes; it successfully achieves a 71% decoding delay reduction while maintaining the same decoding performance as traditional schemes. [38] studies the min-sum algorithm decoding approach and proposes both a neural normalized min-sum network (NNMS) and a shared neural normalized min-sum network (SNNMS). The latter network is used to reduce the number of correction factors while also making use of the advantages of modeldriven DL methods.…”

“…The concept of optimizing channel resources was studied in [27] when it utilized a 2D and 3D CNN network with a ReLU activation function to learn the non-linear structural characteristics of the channel, extract the channel feature vectors to compress the data for further use and when [26] used a flexible denoising convolutional neural network on a cell-free mmWave massive MIMO system to exploit an accurate estimation of CSI. Liao et al [27] implemented a Bi-LSTM and Bi-ConvLSTM network in the [25], [36], [37], [38] • Developing error correction codes for nonlinear channels…”

Two Novel Semi-/Auto-Adaptive SNR Algorithms to Efficiently Train Deep Neural SPA Decoders

“…Lugosch et al [17] proposed to apply deep learning technology to the offset min-sum algorithm (OMS) to achieve similar decoding performance as that in [13], while requiring fewer trainable parameters and lower hardware complexity. Wang et al [18] adopted modeldriven deep learning and proposed shared neural normalized min-sum (SNNMS) decoding to reduce the number of correction factors and lower the complexity. Vasić et al [19] utilized DNNs to MSA for decoding LDPC codes.…”