Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Ziqing, Cho, Myung, Jin, Qiutong, Xu, Weiyu
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.00076
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • We consider a neural network (NN) that may experience memory faults and computational errors. In this paper, we propose a novel real-number-based error correction code (ECC) capable of detecting and correcting both memory errors and computational errors. The proposed approach introduces structures in the form of real-number-based linear constraints on the NN weights to enable error detection and correction, without sacrificing classification performance or increasing the number of real-valued NN parameters.