Deep learning II - III Batch Normalization - Normalizing activation in a network 激励函数输出归一化
Posted dqhl1990
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了Deep learning II - III Batch Normalization - Normalizing activation in a network 激励函数输出归一化相关的知识，希望对你有一定的参考价值。
Normalizing activation in a network 激励函数输出归一化
之前我们提到过将输入归一化，能够使学习加速；但是，由于深度神经网络的层数较多，每一层的输出又会变成下一层的输入，因此对于每一层
z[l]
z
[
l
]
(常用，应作为default)或者
a[l]
a
[
l
]
的输出进行归一化，同样能够加速学习。
如何计算Batch Norm
如何在mini-batch中实现Batch Norm
以上是关于Deep learning II - III Batch Normalization - Normalizing activation in a network 激励函数输出归一化的主要内容，如果未能解决你的问题，请参考以下文章
Deep learning III - II Machine Learning Strategy 2 - Multi-task Learning 多任务学习
Deep learning III - II Machine Learning Strategy 2 - Mismatched training and dev/test set
Deep learning III - II Machine Learning Strategy 2 - Bias and Variance with mismatched data distribu
Deep learning II - III Batch Normalization - Normalizing activation in a network 激励函数输出归一化
Deep learning III - I Machine Learning Strategy - improving your model performance 如何减少可变避免的变差和方差
Deep learning III - I Machine Learning Strategy - train development and test sets 训练集开发集和测试集