… Deep learning methods are also a current focus of research in … codes can be used as
binary linear block codes, which means this neural network decoder may also decode RS codes …

… Deep Learning (DL), which belongs to a class of ML algorithms, that uses multiple layers of
non linear … With the advent of training techniques such as layer-by-layer unsupervised pre-…

… in a non-linear way) the aggregate activation of the network. Deep Learning in NNs is about
… Learning methods for such RNNs are expected to become even much more important than …

… deep learning (DL) methods to optimize polar belief propagation (BP) decoding and concatenated
LDPC-polar codes. First, … Polar codes are a type of linear block codes that exploit the …

… This section formally defines Polar codes and motivates our method. … Binary linear codes
with optimal scaling: Polar codes with large kernels. IEEE Transactions on Information Theory, …

… the deep learning framework for decoding linear block codes has … The work [10] uses deep
learning methods to improve the … for linear codes in Section III and non-linear block codes in …

… applying deep learning techniques to find an alternative decoding algorithm of Polar codes
in flat … The activation functions used in this paper are sigmoid and rectified linear unit (ReLU), …

… Kim, Lapidoth, and Weissman showed that linear codes that utilize the noisy output … We
demonstrated the effectiveness of the neural network technique in achieving superior reliability …

… the codes in real time. In this study, we applied deep learning techniques to compute the
codes. A … patterns (on a linear scale) coded by genetic algorithm and deep learning approach. …

… However, previously published methods are still relatively simple in comparison to the …
methods or supervised machine learning with linear models and manual feature engineering. …