Belief Propagation for Error Correcting Codes and Lossy Compression Using Multilayer Perceptrons

TL;DR

This paper explores the potential and limitations of belief propagation algorithms as decoders for error correcting codes and lossy compression schemes based on multilayer perceptrons, highlighting theoretical promise and practical challenges.

Contribution

It investigates the applicability of belief propagation in multilayer perceptron-based coding schemes, revealing both its limitations in fully connected networks and the complex structure of solution spaces.

Findings

BP shows strong limitations in fully connected networks.

Theoretical results indicate promising aspects of BP in these schemes.

Solution space may have a rich and complex structure.

Abstract

The belief propagation (BP) based algorithm is investigated as a potential decoder for both of error correcting codes and lossy compression, which are based on non-monotonic tree-like multilayer perceptron encoders. We discuss that whether the BP can give practical algorithms or not in these schemes. The BP implementations in those kind of fully connected networks unfortunately shows strong limitation, while the theoretical results seems a bit promising. Instead, it reveals it might have a rich and complex structure of the solution space via the BP-based algorithms.