csn231SettingUpTheDataAndTheModel

最新推荐文章于 2023-03-13 17:27:56 发布

svdalv

最新推荐文章于 2023-03-13 17:27:56 发布

阅读量428

点赞数

CC 4.0 BY-SA版权

分类专栏：深度学习

本文链接：https://blog.youkuaiyun.com/ns708865818/article/details/72764187

深度学习专栏收录该内容

7 篇文章

订阅专栏

本文详细介绍深度学习模型的建立过程，包括数据预处理、权重初始化等关键步骤，并探讨了如何通过正则化、批量归一化等技术防止过拟合，最后介绍了几种常见的损失函数。

#####################
setting up the data and the model
Data Preprocessing
Weight Initilization
Batch Normalization
Regularization(L2/L1/Maxnorm/Dropout)
#######################
Loss functions
#######################
summary
#######################
Data Preprocessing
Method1
Mean subtraction
Normalization
Method2
PCA and Whitening
Common pitfall:
the mean must be computed only over the training data
and then subtracted equally from all splits (train/val/test).
#######################
Weight Initialization
1.Small random numbers
2.Calibrating the variance with 1/sqt(n)
3.Sparse initialization
Initizaling the biases
Batch Normalization is in practice
#######################
How to prevent over-fitting
Regularization
L2 regularization
L1 regularization
Max norm constraints
Dropout
Theme of noise in forward pass
Bias regularization
Pre-layer regularization
########################
Loss Functions
when large number of classes
Hiearchical sofmax
Attribute classification
Regression