… concepts of convolutional coding and its applications. This book is suitable for use as a
textbook in a one-term course on coding theory with emphasis on convolutional codes. Senior …

… , we compare deep residual network and other deep learning … deep learning-based
convolutional codes blind identification system, and then describe the basic theory of deep learning. …

… learning based coding. Inspired by convolutional codes, we use hierarchical convolutional
… Due to great progresses have been made by deep learning in a variety of areas, DNN has …

… our paper, deep learning fits well with CS decoding for both FL CS codes and VL CS codes,
which … ReLU is used as the activation function for each convolutional layer. We note that CS …

… (1) Focusing on convolutional codes we aim to decode them on … deep models, namely
recurrent neural networks. We consider the basic sequential code known as convolutional codes, …

… Also shown as baselines are the state-of-the art polar, LDPC, and tail-bitting convolutional
codes (TBCC) in a 3GPP document for the 5G meeting [29] (we refer to Appendix A for the …

… family of codes obtained via deep learning, which significantly outperforms state-of-the-art
codes … small error rate, including convolutional codes, Turbo codes, LDPC codes, and polar …

… the question whether structured codes are easier to “learn” than random codes, and whether
a … This limits the NND to short codes. However, the NN decoder for convolutional codes was …

… In [6], Swaminathan and Madhukumar proposed a classification algorithm to distinguish
the linear block codes, convolutional codes, and uncoded random bits, through computing the …

… To fill this gap, we trained deep convolutional neural networks to predict the firing rates of
V1 neurons in response to natural image stimuli, and we find that the predicted firing rates are …