Effect of Batch Normalization on Noise Resistant Property of Deep Learning Models
This addresses a practical problem for edge computing with analog hardware, where noise can degrade model performance, but the findings are incremental as they focus on a specific layer's impact.
The study investigated how batch normalization affects the noise resistance of deep learning models deployed on analog hardware, finding that batch normalization layers reduce noise resistance, with performance degradation increasing as more layers are added.
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.