为神经网络设计可检测纠错的实数编码，不增加参数量
Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network
- 用实数线性约束构造神经网络权重纠错结构
- 能同时检测修正内存与计算错误，性能不变
- 适合高可靠性场景如自动驾驶、医疗诊断
我们研究可能遭遇内存故障和计算误差的神经网络。本文提出一种新型基于实数的错误纠正码（ECC），可检测并纠正内存错误与计算错误。该方法通过在神经网络权重上引入实数线性约束结构，实现错误检测与纠正，无需牺牲分类性能，也不增加实数参数数量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。