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.
@article{arxiv.2602.00076,
title = {Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network},
author = {Ziqing Li and Myung Cho and Qiutong Jin and Weiyu Xu},
journal= {arXiv preprint arXiv:2602.00076},
year = {2026}
}