Offset min-sum Optimization for General Decoding Scheduling: A Deep Learning Approach

Abotabl, Ahmed Attia; Bae, Jung Hyun; Song, Kee-Bong

doi:10.1109/vtcfall.2019.8891434

Cited by 10 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we further consider its simplifications, type-6 and-type 7, which assign parameters only based on horizontal layers and vertical layers, respectively. Finally, type 8 decoder assigns iteration-distinct parameters, this simple weight sharing schemes have been considered for previous literature [11], [14].…”

Section: Neural 2d Normalized Minsum Decodersmentioning

confidence: 99%

“…The focus on short codes may result from the fact that popular deep learning research platforms, such as Pytorch and Tensorflow, require large amounts of memory to calculate the gradient when the block length is long. However, as pointed in [11], it is possible to train the parameters for longer block lengths if resources are handled more efficiently. Abotabl et al provided an efficient computation framework for optimizing the offset values in the N-OMS algorithm [11], and trained an OMS neural network with edge-specific weights, iteration-specific weights, and a single weight.…”

Section: Introductionmentioning

confidence: 99%

“…However, as pointed in [11], it is possible to train the parameters for longer block lengths if resources are handled more efficiently. Abotabl et al provided an efficient computation framework for optimizing the offset values in the N-OMS algorithm [11], and trained an OMS neural network with edge-specific weights, iteration-specific weights, and a single weight.…”

Section: Introductionmentioning

confidence: 99%

“…• An efficient implementation of the N-NMS architecture based on the gradients in backpropagation. This part is related to the framework in [11]. We show that backpropagation can be conducted in an iterative way, and the parameters used to implement backpropagation can be stored efficiently.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Neural-Network-Optimized Degree-Specific Weights for LDPC MinSum Decoding

Wang

Chen

Nguyen

et al. 2021

Preprint

View full text Add to dashboard Cite

Neural Normalized MinSum (N-NMS) decoding delivers better frame error rate (FER) performance on linear block codes than conventional normalized MinSum (NMS) by assigning dynamic multiplicative weights to each check-to-variable message in each iteration. Previous N-NMS efforts have primarily investigated short-length block codes (N < 1000), because the number of N-NMS parameters to be trained is proportional to the number of edges in the parity check matrix and the number of iterations, which imposes am impractical memory requirement when Pytorch or Tensorflow is used for training. This paper provides efficient approaches to training parameters of N-NMS that support N-NMS for longer block lengths. Specifically, this paper introduces a family of neural 2-dimensional normalized (N-2D-NMS) decoders with with various reduced parameter sets and shows how performance varies with the parameter set selected. The N-2D-NMS decoders share weights with respect to check node and/or variable node degree. Simulation results justify this approach, showing that the trained weights of N-NMS have a strong correlation to the check node degree, variable node degree, and iteration number. Further simulation results on the (3096,1032) protograph-based raptor-like (PBRL) code show that N-2D-NMS decoder can achieve the same FER as N-NMS with significantly fewer parameters required. The N-2D-NMS decoder for a (16200,7200) DVBS-2 standard LDPC code shows a lower error floor than belief propagation. Finally, a hybrid decoding structure combining a feedforward structure with a recurrent structure is proposed in this paper. The hybrid structure shows similar decoding performance to full feedforward structure, but requires significantly fewer parameters.

show abstract

Section: Neural 2d Normalized Minsum Decodersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural-Network-Optimized Degree-Specific Weights for LDPC MinSum Decoding

Wang

Chen

Nguyen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning supplemented communication systems have shown the potential to further enhance the system's performance [1], [20]- [23]. In particular, for the detection and decoding algorithms, the research on autoencoders [24] and the NN optimization schemes which transform the FGs into NN systems [25], [26], has drawn significant interests.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Assisted Sum-Product Detection Algorithm for Faster-than-Nyquist Signaling

Liu

Xie

et al. 2019

2019 IEEE Information Theory Workshop (ITW)

View full text Add to dashboard Cite

A deep learning assisted sum-product detection algorithm (DL-SPA) for faster-than-Nyquist (FTN) signaling is proposed in this paper. The proposed detection algorithm concatenates a neural network to the variable nodes of the conventional factor graph of the FTN system to help the detector converge to the a posterior probabilities based on the received sequence. More specifically, the neural network performs as a function node in the modified factor graph to deal with the residual intersymbol interference (ISI) that is not modeled by the conventional detector with a limited number of ISI taps. We modify the updating rule in the conventional sum-product algorithm so that the neural network assisted detector can be complemented to a Turbo equalization. Furthermore, a simplified convolutional neural network is employed as the neural network function node to enhance the detector's performance and the neural network needs a small number of batches to be trained. Simulation results have shown that the proposed DL-SPA achieves a performance gain up to 2.5 dB with the same bit error rate compared to the conventional sum-product detection algorithm under the same ISI responses.

show abstract