Learning to decode linear codes using deep learning

By Eliya Nachmani, Yair Be’ery, David Burshtein. Allerton Conference on Communication, Control, and Computing, 2016

521 citations recorded by the source corpus.

A novel deep learning method for improving the belief propagation algorithm is proposed. The method generalizes the standard belief propagation algorithm by assigning weights to the edges of the Tanner graph. These edges are then trained using deep learning techniques. A well-known property of the belief propagation algorithm is the independence of the performance on the transmitted codeword. A crucial property of our new method is that our decoder preserved this property. Furthermore, this property allows us to learn only a single codeword instead of exponential number of codewords. Improvements over the belief propagation algorithm are demonstrated for various high density parity check codes.

Subfields: Computer Networks and Communications, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/1ddd174935c7bb4f0c341273f541da14cf8aa5d8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Molecular Biology

Citations in the corpus

An Introduction to Deep Learning for the Physical Layer (2017, methodology): “Among the papers trying to improve existing algorithms are [22]–[24] that consider belief propagation channel decoding and multiple-input multiple-output (MIMO) detection, respectively.”
Deep Learning Based Communication Over the Air (2017, background): “Thus, ı̂ ∈ [− Nmsg/2 , (Nmsg − 1)/2 ] For example, for Nmsg = 16, τ ∈ [1, 16] is mapped to ı̂ ∈ [−8, 7].”
On deep learning-based channel decoding (2017, methodology): “For instance, in [15], weights are assigned to the Tanner graph of the belief propagation (BP) algorithm and learned by NN techniques in order to improve the BP algorithm.”
Deep MIMO detection (2017, methodology): “In recent years, deep learning methods have been purposed for improving the performance of a decoder for linear codes in fixed channels[13].”
Deep Learning for Intelligent Wireless Networks: A Comprehensive Survey (2018, background): “In [44] and [45], the belief propagation (BP) decoding algorithm of the low-density parity-check (LDPC) codes is improved by DL.”
Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels (2019, methodology): “In [4], the traditional belief-propagation decoding algorithm is extended as deep learning layers to decode linear codes.”
A Deep Learning Framework for Optimization of MISO Downlink Beamforming (2019, background): “A lot of research has attempted to use DL to address physical layer issues, including channel decoding [17, 18], detection [19–21], channel estimation [22–24], and resource management [25–32].”
Learning to Detect (2018, background): “Exciting contributions in the context of error correcting codes include [17]–[21].”
Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems (2017, methodology): “applied in localization based on CSI [3], channel equalization [5], and channel decoding [4] in communication systems.”
Grant-Free Non-Orthogonal Multiple Access for IoT: A Survey (2019, methodology): “For the physical layer, learning algorithms have been applied to demodulation [180], channel codes [181], BP for channel decoding [182], one-shot channel decoding [183], CS [184], coherent [185], and blind [186] detection.”
Neural Network Detection of Data Sequences in Communication Systems (2018, background): “Some examples of machine learning tools applied to design problems in communication systems include multiuser detection in code-division multiple-access (CDMA) systems [12]–[15], decoding of linear codes [16], design of new modulation and demodulation schemes [17], [18], detection and channel decodi”
Channel Agnostic End-to-End Learning Based Communication Systems with Conditional GAN (2018, unknown): “system, including the multiple-input and multiple-output (MIMO) detection [1], [2], channel decoding [3], and channel estimation [4], [5].”