Metraipolis › archive › dc_f5793ac97ded

ESupNNet: An Error Supervising Neural Network architecture for error detection against soft errors in parameters — arXiv:2609.26374

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26374
License (as archived)
CC0-1.0
Archived
2026-10-08T14:37:39.979Z
SHA-256 of the archived text
530bafb7da2d2b0fa68e87bcd10006180b42783d06dea962e7817818eae47669
Stable URL of this page
https://metraipolis.com/documento/dc_f5793ac97ded

How to cite

ESupNNet: An Error Supervising Neural Network architecture for error detection against soft errors in parameters — arXiv:2609.26374 — arXiv (en), https://arxiv.org/abs/2609.26374 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5793ac97ded (Metraipolis archive dc_f5793ac97ded, sha256 530bafb7da2d2b0fa68e87bcd10006180b42783d06dea962e7817818eae47669)
BibTeX
@misc{dcf5793ac97ded,
  title = {ESupNNet: An Error Supervising Neural Network architecture for error detection against soft errors in parameters — arXiv:2609.26374},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26374},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5793ac97ded; sha256 530bafb7da2d2b0fa68e87bcd10006180b42783d06dea962e7817818eae47669},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26374. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This work presents a novel approach to detect misclassification errors in CNNs caused by soft errors in their parameters. We propose an architecture that uses inter-class relations induced by the CNN that needs protection. The architecture has minimal resources overhead and does not require modifying the CNN, which makes it a competent solution that can be used with other error protection techniques. We have validated the architecture with five different combinations of modern dataset-model pairs: ImageNet-1K for ResNet-50 and EfficientNetV2-Small; CIFAR-10 for MobileNetV3, ShuffleNetV2-Small with 2.0x output channels and MNASNet with depth multiplier of 1.3. The validation process was done rigorously with statistical significance, from the creation of the datasets used by the architecture to the acquisition of experimental results. Results show great performance with over 90% accuracy in detecting single errors and great error detection over multiple Bit Error Rates, which can be potentially increased with hyperparameter tuning.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AR).
Categorie arXiv: Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2609.26374 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:47:52.528Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).