A Learning-Based Approach to Address Complexity-Reliability Tradeoff in OS Decoders

03/05/2021
by   Baptiste Cavarec, et al.
0

In this paper, we study the tradeoffs between complexity and reliability for decoding large linear block codes. We show that using artificial neural networks to predict the required order of an ordered statistics based decoder helps in reducing the average complexity and hence the latency of the decoder. We numerically validate the approach through Monte Carlo simulations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/09/2019

Segmentation-Discarding Ordered-Statistic Decoding for Linear Block Codes

In this paper, we propose an efficient reliability based segmentation-di...
research
04/30/2021

Anytime Decoding by Monte-Carlo Tree Search

An anytime decoding algorithm for tree codes using Monte-Carlo tree sear...
research
04/07/2023

Diversity Preserving, Universal Hard Decision Decoder for Linear Block Codes

Hard-decision decoding does not preserve the diversity order. This resul...
research
08/22/2023

Fast Gao-like Decoding of Horizontally Interleaved Linearized Reed-Solomon Codes

Both horizontal interleaving as well as the sum-rank metric are currentl...
research
06/01/2020

Latency and Reliability Limits with Decoding Complexity Constraints

One of the most important application scenarios in next-generation wirel...
research
07/13/2023

Deep learning based enhancement of ordered statistics decoding of LDPC codes

Aiming at designing plausible decoders with channel information free, lo...
research
02/14/2020

Consistency Analysis of Replication-Based Probabilistic Key-Value Stores

Partial quorum systems are widely used in distributed key-value stores d...

Please sign up or login with your details

Forgot password? Click here to reset