Deep Learning Methods for Improved Decoding of Linear Codes
By Eliya Nachmani, Elad Marciano, Loren Lugosch, Warren J. Gross, David Burshtein, Yair Be’ery. IEEE Journal on Selected Topics in Signal Processing, 2017
552 citations recorded by the source corpus.
The problem of low complexity, close to optimal, channel decoding of linear codes with short to moderate block length is considered. It is shown that deep learning methods can be used to improve a standard belief propagation decoder, despite the large example space. Similar improvements are obtained for the min-sum algorithm. It is also shown that tying the parameters of the decoders across iterations, so as to form a recurrent neural network architecture, can be implemented with comparable results. The advantage is that significantly less parameters are required. We also introduce a recurrent neural decoder architecture based on the method of successive relaxation. Improvements over standard belief propagation are also observed on sparser Tanner graph representations of the codes. Furthermore, we demonstrate that the neural belief propagation decoder can be used to improve the performance, or alternatively reduce the computational complexity, of a close to optimal decoder of short BCH codes.
View Paper: https://www.semanticscholar.org/paper/36ef340614ca97bdc2a55839b9529b204887eda6
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Qingqing Wu
- N. Rajatheva
- Hadi Sarieddeen
- Deniz Gündüz
- Italo Atzeni
- Osvaldo Simeone
- E. Bjornson
- Stefano Buzzi
Citations in the corpus
- A Very Brief Introduction to Machine Learning With Applications to Communication Systems (2018, methodology): “related to channel decoding, in [36] and [37], knowledge of the near-optimality of message passing methods for the decoding of sparse graphical codes is used to set up a parameterized”
- White Paper on Broadband Connectivity in 6G (2020, background): “Furthermore, modified polar code constructions can be adopted to improve the performance of iterative algorithms, potentially with the aid of machine learning such as deep unfolding [98, 99].”
- Deep Joint Source-channel Coding for Wireless Image Transmission (2018, unknown): “Some examples of such designs include decoder design for existing channel codes [12], [13], blind channel equalization [14], learning physical layer signal representation for SISO [11] and MIMO [15] systems, OFDM systems [16], [17], JSCC of text messages [18] and JSCC for MNIST images for analog sto”
- Machine Learning for Wireless Networks with Artificial Intelligence: A Tutorial on Neural Networks (2017, unknown): “The existing works such as [33]–[37] have studied a number of problems related to the use of ANNs for physical layer design such as signal detection in [33] and [37], learning transmitted symbols in [34], channel decoding in [35] and [36].”
- DeepJSCC-f: Deep Joint Source-Channel Coding of Images With Feedback (2019, background): “deep learning for various classification tasks, researchers first explored using DNNs to decode existing channel codes, such as linear [23], turbo [24], or polar [25] codes, which pro-”
- A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art (2019, unknown): “s) [349]. For example, ML and neural networks can be used for channel estimation and signal detection [350], [351], localization based on channels state information [352], [353], and channel decoding [354], which all show that ML is a promising tool in wireless communications. ● Second, the design a”