论文标题
关于深神经网络中卷积层的不确定性的研究
A Study on the Uncertainty of Convolutional Layers in Deep Neural Networks
论文作者
论文摘要
本文显示了在神经网络结构（即LENET）中卷积层的连接权重中存在的最小属性。具体而言，Min-Max属性意味着，在基于背部的LENET训练中，卷积层的重量将远离其间隔中心，即减小到最小值或增加到最大。从不确定性的角度来看，我们证明了Min-Max属性对应于通过简化的卷积公式来最大程度地减少模型参数的模糊性。可以通过实验证实，具有最小最大特性的模型具有更强的对抗性鲁棒性，因此可以将该特性纳入损失函数的设计中。本文指出，LENET结构的卷积层中不确定性的趋势发生了变化，并为卷积的解释性提供了一些见解。
This paper shows a Min-Max property existing in the connection weights of the convolutional layers in a neural network structure, i.e., the LeNet. Specifically, the Min-Max property means that, during the back propagation-based training for LeNet, the weights of the convolutional layers will become far away from their centers of intervals, i.e., decreasing to their minimum or increasing to their maximum. From the perspective of uncertainty, we demonstrate that the Min-Max property corresponds to minimizing the fuzziness of the model parameters through a simplified formulation of convolution. It is experimentally confirmed that the model with the Min-Max property has a stronger adversarial robustness, thus this property can be incorporated into the design of loss function. This paper points out a changing tendency of uncertainty in the convolutional layers of LeNet structure, and gives some insights to the interpretability of convolution.
