论文标题
批处理标准化对深度学习模型抗噪声特性的影响
Effect of Batch Normalization on Noise Resistant Property of Deep Learning Models
论文作者
论文摘要
模拟硬件的快速执行速度和能源效率使它们成为了在边缘部署深度学习模型的强大竞争者。但是，人们担心模拟噪声的存在会导致模型的重量变化，尽管它们具有固有的抗噪声特征，但导致深度学习模型的性能下降。在这项工作中研究了流行的批准层归一层对深度学习模型噪声能力的影响。这项系统的研究是通过在CIFAR10和CIFAR100数据集上进行有没有批次归一化层的第一个训练不同模型进行的。然后将所得模型的权重注入模拟噪声，并获得测试数据集上模型的性能并比较。结果表明，批处理归一层的存在对深度学习模型的抗噪声性特性产生负面影响，并且随着批处理标准化层数量的增加而增长的影响。
The fast execution speed and energy efficiency of analog hardware has made them a strong contender for deployment of deep learning model at the edge. However, there are concerns about the presence of analog noise which causes changes to the weight of the models, leading to performance degradation of deep learning model, despite their inherent noise resistant characteristics. The effect of the popular batch normalization layer on the noise resistant ability of deep learning model is investigated in this work. This systematic study has been carried out by first training different models with and without batch normalization layer on CIFAR10 and CIFAR100 dataset. The weights of the resulting models are then injected with analog noise and the performance of the models on the test dataset is obtained and compared. The results show that the presence of batch normalization layer negatively impacts noise resistant property of deep learning model and the impact grows with the increase of the number of batch normalization layers.
