preprint · arXiv (Cornell University) · 2020

Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding

Cited by 1Open access

Abstract

Ensemble models are widely used to solve complex tasks by their decomposition into multiple simpler tasks, each one solved locally by a single member of the ensemble. Decoding of error-correction codes is a hard problem due to the curse of dimensionality, leading one to consider ensembles-of-decoders as a possible solution. Nonetheless, one must take complexity into account, especially in decoding. We suggest a low-complexity scheme where a single member participates in the decoding of each word. First, the distribution of feasible words is partitioned into non-overlapping regions. Thereafter, specialized experts are formed by independently training each member on a single region. A classical hard-decision decoder (HDD) is employed to map every word to a single expert in an injective manner. FER gains of up to 0.4dB at the waterfall region, and of 1.25dB at the error floor region are achieved for two BCH(63,36) and (63,45) codes with cycle-reduced parity-check matrices, compared to the previous best result of [1].

Cite this paper

APA 7

Raviv, T., Raviv, N., & Be'ery, Y. (2020). Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding. arXiv (Cornell University), 321–326. https://doi.org/10.1109/isit44484.2020.9173971

MLA 9

Raviv, Tomer, et al. “Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding.” arXiv (Cornell University), 2020, pp. 321–26, https://doi.org/10.1109/isit44484.2020.9173971.

Chicago

Raviv, Tomer, Nir Raviv, and Y. Be'ery. 2020. “Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding.” arXiv (Cornell University): 321–26. https://doi.org/10.1109/isit44484.2020.9173971.

Harvard

Raviv, T., Raviv, N. and Be'ery, Y. (2020) ‘Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding’, arXiv (Cornell University), pp. 321–326. Available at: https://doi.org/10.1109/isit44484.2020.9173971.

BibTeX

@misc{raviv2020data,
  title = {{Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding}},
  author = {Raviv, Tomer and Raviv, Nir and Be'ery, Y.},
  journal = {arXiv (Cornell University)},
  pages = {321--326},
  year = {2020},
  doi = {10.1109/isit44484.2020.9173971}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.