A unified method to construct neural network decoders for arbitrary codes and decoding rules Original Research Article

This paper presents a unified method to construct decoders which are implemented by a feedforward neural network. By setting the parameters of the network, it can decode any given code {(ci,Di); i=1,…,M}. We focus on the case that the sets D1,…,DM are weighted distance spheres. Properties and constructions of weighted distance spheres are developed. Weighted distance perfect codes are defined and studied. Finally, the complexity of the network decoder is discussed.