Information Geometrical Framework for Analyzing Belief Propagation Decoder
Abstract
The mystery of belief propagation (BP) decoder, especially of the turbo decoding, is studied from information geometrical viewpoint. The loopy belief network (BN) of turbo codes makes it difficult to obtain the true “belief” by BP, and the characteristics of the algorithm and its equilib- rium are not clearly understood. Our study gives an intuitive understand- ing of the mechanism, and a new framework for the analysis. Based on the framework, we reveal basic properties of the turbo decoding.
Cite
Text
Ikeda et al. "Information Geometrical Framework for Analyzing Belief Propagation Decoder." Neural Information Processing Systems, 2001.Markdown
[Ikeda et al. "Information Geometrical Framework for Analyzing Belief Propagation Decoder." Neural Information Processing Systems, 2001.](https://mlanthology.org/neurips/2001/ikeda2001neurips-information/)BibTeX
@inproceedings{ikeda2001neurips-information,
title = {{Information Geometrical Framework for Analyzing Belief Propagation Decoder}},
author = {Ikeda, Shiro and Tanaka, Toshiyuki and Amari, Shun-ichi},
booktitle = {Neural Information Processing Systems},
year = {2001},
pages = {407-414},
url = {https://mlanthology.org/neurips/2001/ikeda2001neurips-information/}
}