We investigate the perspectives of utilizing deep neural networks (DNN) to decode Low-Density Parity Check (LDPC) codes. The main idea is to build a neural network to learn and optimize a conventional iterative decoder of LDPC codes. A DNN is based on Tanner graph, and the activation functions emulate message update functions in variable and check nodes. We impose a symmetry on weight matrices which makes it possible to train the DNN on a single codeword and noise realizations only. Based on the trained weights and the bias, we further quantize messages in such DNN-based decoder with low precision while maintaining no loss in error performance compared to the traditional algorithms. The goal is to make the iterative DNN decoder converge faster and thus achieve higher throughput at the cost of trivial additional decoding complexity.
- Xin Xiao
- Bane Vasic
- NSF Grant ECCS-1500170
- Indo-US Science and Technology Forum - JC-16-2014-US
|BibTeX||B. Vasić, X. Xiao, and S. Lin, "Learning to Decode LDPC Codes with Finite-Alphabet Message Passing," Information Theory and Applications Workshop (ITA 2018), Feb. 11-16 2018, pp. 1-10.|