用于容错深度神经网络的重心引导权重校正
CoG-Guided Weight Correction for Fault-Tolerant Deep Neural Networks
查看机构详情
- TalTech（塔林理工大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
研究安全关键应用中深度神经网络易受硬件故障影响的问题，提出基于重心引导的权重校正方法，利用距离感知规则检测和校正故障，在多种网络实验中显著提升容错能力，是首将CoG用于神经网络权重张量提高可靠性的工作。
中文摘要 AI 辅助
用于安全关键应用的深度神经网络容易受到硬件和内存故障的影响，这些故障会破坏网络权重并降低可靠性。本文提出了一种重心（CoG）引导的权重校正方法，该方法根据每层中权重的空间特征来恢复错误的权重。所提出的方法使用距离感知校正规则来检测和校正权重故障，无需重新训练或修改架构。通过在不同误码率（BER）下进行故障注入，评估了该方法在容忍硬件故障方面的有效性。在基于安全关键的长短期记忆网络上的实验，包括用于疾病进展跟踪的StageNet和用于心脏异常检测的MTFNet，在BER为10^-3时，容错能力分别提高了230倍和6.41倍，精度损失可忽略不计。当扩展到卷积神经网络时，该方法在可比故障条件下，在ResNet-18和VGG-16上分别实现了高达49.55倍和20.79倍的改进。据我们所知，这是第一项将CoG概念应用于神经网络权重张量以提高模型可靠性的工作。
英文摘要
Deep Neural Networks (DNNs) used in safety-critical applications are vulnerable to hardware and memory faults that corrupt network weights and degrade reliability. In this paper, we propose a Center of Gravity (CoG) guided weight correction method that restores faulty weights based on their spatial characteristics within each layer. The proposed approach detects and corrects weight faults using distance-aware correction rules, eliminating the need for retraining or architectural modification. The effectiveness of the proposed method in terms of the capability of tolerating hardware faults has been evaluated through performing fault injection at different Bit Error Rates (BERs). Experiments on safety-critical LSTM-based Networks, including StageNet for disease progression tracking and MTFNet for cardiac anomaly detection, demonstrate fault tolerance improvements of up to 230x and 6.41x, respectively, at a BER of 10^{-3}, with negligible accuracy loss. When extended to Convolutional Neural Networks (CNNs), the method achieves up to 49.55x and 20.79x improvements under comparable fault conditions on ResNet-18 and VGG-16, respectively. To the best of our knowledge, this is the first work to apply the CoG concept to neural network weight tensors for enhancing model reliability.
