… In this paper we suggest an application of deep learning methods to the problem of low …
linear error correcting codes are the linear low-density parity-check (LDPC) codes [5]. LDPC …

… In this work we applied deep learning techniques to improve the performance of the BP
algorithm. We showed that a “soft” Tanner graph can produce improvements when used in the …

… Abstract—We present a novel framework for applying deep neural networks (DNN) to soft
decoding of linear codes at arbitrary block lengths. Unlike other approaches, our framework …

… Data is a vital part of deep learning methods, yet we see that it is not fully comprehended.
Many researchers focus on preliminary choice of training data, followed by passive generation …

… Essentially, we provide a deep learning-based method to obtain a good set of parameters
and … We consider binary linear codes C of length N, each specified by an M × N PC matrix H. …

… We propose training methods that discover novel non-linear codes when trained over … of
non-linear codes, KO codes, that strictly generalize and improve upon RM codes by capitalizing …

… CLCNet, a framework based on complex valued linear coding. First, we define complex
linear coding (CLC) motivated by linear predictive coding (LPC) that is applied in the complex …

… of codes obtained via deep learning, which significantly beats state-of-the-art codes designed
… This is especially troubling since all practical codes are linear and linear codes are known …

… that no linear code … codes are linear and linear codes are known to achieve capacity (without
feedback) [10], whereas [9] proposes an asymptotically optimal and nonlinear coding …

… deep learning-based ECC decoding. In [33], the authors proposed recurrent neural network
(RNN)-based decoding for linear codes, … deep learning-based decoding for CS codes. As we …