Metraipolis › archive › dc_62833d2da777

RobustNCL: Robustifying Neuromorphic Continual Learning under Transient Faults with Lightweight Detect-and-Cure Strategy — arXiv:2610.31954

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31954
License (as archived)
CC0-1.0
Archived
2026-10-26T19:51:35.395Z
SHA-256 of the archived text
ea4a38d11240832d58392766e5607e82127274e72d7536a32b68dd18b3c36d5d
Stable URL of this page
https://metraipolis.com/documento/dc_62833d2da777

How to cite

RobustNCL: Robustifying Neuromorphic Continual Learning under Transient Faults with Lightweight Detect-and-Cure Strategy — arXiv:2610.31954 — arXiv (en), https://arxiv.org/abs/2610.31954 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62833d2da777 (Metraipolis archive dc_62833d2da777, sha256 ea4a38d11240832d58392766e5607e82127274e72d7536a32b68dd18b3c36d5d)
BibTeX
@misc{dc62833d2da777,
  title = {RobustNCL: Robustifying Neuromorphic Continual Learning under Transient Faults with Lightweight Detect-and-Cure Strategy — arXiv:2610.31954},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31954},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62833d2da777; sha256 ea4a38d11240832d58392766e5607e82127274e72d7536a32b68dd18b3c36d5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31954. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In neural networks, continual learning (CL) is a prominent approach for enabling deployed systems to adapt to dynamic operational environments by effectively learning from new unseen data at runtime. Recently, the neuromorphic continual learning (NCL) concept has emerged as an energy-efficient alternative to CL by leveraging sparse event-based operations. However, NCL performance can be undermined by transient faults in the hardware platforms, which may come from high-energy particle strikes at any time. Currently, NCL reliability under transient faults has not been studied, and hence the corresponding fault-tolerance techniques remain unexplored. To address this, we propose a novel RobustNCL framework to improve NCL reliability in the presence of transient faults in the DRAM-based off-chip memory of hardware platforms through a lightweight detect-and-cure strategy. Specifically, it first monitors the presence of faults during weight data access from off-chip memory, and then cures the accessed weights if anomalous signatures are detected. It provides three curing variants: replacement with zero, min/max value, and most-probable value from the original/clean weight distribution. To support this, the weight curing values are stored in the radiation-hardened memory. Experimental results show that, in the presence of high fault rates (e.g., 5x10^{-4} for memory replay), RobustNCL maintains high accuracy close to the accuracy of fault-free models (i.e., within -0.5% accuracy for the best RobustNCL variant) and significantly improves accuracy from the baseline without fault mitigation across different NCL methods and datasets (i.e., Split MNIST, Split Fashion-MNIST, Split CIFAR-10, and Split CIFAR-100), while incurring negligible latency and energy overheads. These results highlight that our RobustNCL framework is a promising approach for enabling reliable and energy-efficient NCL systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.31954 — 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 2026-10-26T19:45:33.372Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).