Blind Decoding-Metric Estimation for Probabilistic Shaping via Expectation Maximization

06/26/2018

∙

by   Fabian Steiner, et al.

∙

0

∙

share

An unsupervised learning approach based on expectation maximization is proposed to obtain the parameters of a soft decision forward error correction decoding metric for probabilistic shaping. The algorithm depends only on the channel observations and does not require transmitted data.