Loading...

Decoding Graph based Linear Codes Using Deep Neural Networks

Malek, Samira | 2020

577 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53215 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Amini, Arash; Saleh Kaleybar, Saber
  7. Abstract:
  8. One of the most important goals we pursue in telecommunications science is to send and receive information from telecommunication channels. By designing a powerful telecommunication system consisting of a transmitter and a receiver, we achieve this goal. Speed of data transmission, accuracy of received information and speed of data extraction are some of the criteria by which the performance of a telecommunication system can be evaluated. No telecommunication channel is free of noise. For this reason, additional information is added to the original information in the transmitter, which can still be extracted if the original information is noisy. This process is called coding. Following coding, we need decoding algorithms to recover information in the receiver. The belief propagation algorithm is one of the decoding methods that has had state of the art results on some linear codes such as LDPC codes.Recently, with the emergence of deep neural networks and the amazing results that have been seen from them, a new approach to decoding has begun. In fact, decoders have been created with the structure of deep neural networks. In the field of neural networks, decoding can be considered as a classification problem. We put each code and its noise in a category. The problem with this approach is the sheer volume of training data. Recently, a new type of neural network has been introduced which is based on the belief propagation algorithm and has taken advantage of the symmetric property of this algorithm and solved the problem of large size of training data. In this thesis, we introduce two new types of neural networks that reduce the bit error rate compared to the belief propagation algorithm and previous networks and also have less complexity. In other words, we have tried to provide decoding algorithms that have higher speed and accuracy than previous decoding networks
  9. Keywords:
  10. Deep Neural Networks ; Linear Code ; Belief Propagation Algorithm ; Neural Decoding ; Low Density Parity Check Codes (LDPC) ; Multilayered Neural Network

 Digital Object List

 Bookmark

No TOC