AI 中文总结
本文提出ESupNNet架构，利用CNN的类间关系检测参数软错误引起的误分类，开销小且无需修改原网络，在多种数据集-模型组合上检测单错误准确率超90%。
AI 中文摘要
本文提出了一种新颖的方法，用于检测由参数中的软错误引起的CNN误分类错误。我们提出了一种架构，利用需要保护的CNN所引发的类间关系。该架构具有最小的资源开销，并且不需要修改CNN，使其成为一种能够与其他错误保护技术结合使用的胜任解决方案。我们使用五种现代数据集-模型组合对该架构进行了验证：ImageNet-1K上的ResNet-50和EfficientNetV2-Small；CIFAR-10上的MobileNetV3、输出通道为2.0倍的ShuffleNetV2-Small以及深度乘数为1.3的MNASNet。验证过程严格且具有统计显著性，从架构所用数据集的创建到实验结果的获取。结果表明，在检测单个错误方面具有超过90%的准确率，并且在多种误码率下具有出色的错误检测性能，该性能可能通过超参数调优进一步提高。
英文摘要
This work presents a novel approach to detect misclassification errors in CNNs caused by soft errors in their parameters. We propose an architecture that uses inter-class relations induced by the CNN that needs protection. The architecture has minimal resources overhead and does not require modifying the CNN, which makes it a competent solution that can be used with other error protection techniques. We have validated the architecture with five different combinations of modern dataset-model pairs: ImageNet-1K for ResNet-50 and EfficientNetV2-Small; CIFAR-10 for MobileNetV3, ShuffleNetV2-Small with 2.0x output channels and MNASNet with depth multiplier of 1.3. The validation process was done rigorously with statistical significance, from the creation of the datasets used by the architecture to the acquisition of experimental results. Results show great performance with over 90% accuracy in detecting single errors and great error detection over multiple Bit Error Rates, which can be potentially increased with hyperparameter tuning.
CommentsThis work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
