一个卷积层，一个归一化层，一个非线性激活函数一起构成了深度卷积神经网络 (ConvNet)的“原子”结构。通过该基础结构的堆叠，产生了许多应用广泛的神经网络。归一化方法是这些神经网络的重要组成部分之一。本次报告的内容围绕深度学习的归一化方法展开，及其为神经网络带来的正则能力与泛化能力。报告分为四个部分。第一部以白化网络（Whitened Neural Network，WNN）为例，浅析神经网络前向计算与反向传播的关系：表明修改前向计算，将可以直接影响深度网络的费希尔信息矩阵 (Fisher …
Meta-learning to learn normalization method for each hidden layer in ConvNet.
Introduce a new family of normalization methods in Deep Learning.
Understanding Batch Normalization in deep learning.
Understanding batch normalization in Deep Learning. This blog was written in Chinese.
Understanding Normalization Methods in Deep Learning.