What is the appropriate Method to normalize inputs data ????
显示 更早的评论
I used sigmoidal function as activation function in hidden layer (forecasting issues).who is interval can i choose to normalize my inputs datasets [-1,1] or [0.1,0.9] ?? and how can i do it ?? by default i used these following commands :
net.inputs{1}.processFcns = {'removeconstantrows','mapminmax'};
net.outputs{2}.processFcns = {'removeconstantrows','mapminmax'};
采纳的回答
Greg Heath
2015-3-28
1 个投票
The data is automatically normalized in the training function. You do not have to do anything extra except to make sure that your input and target data don't have any errors or outliers.
As far as outlier detection is concerned, I typically use zscore BEFORE training.
Hope this helps.
Thank you for formally accepting my answer
Greg
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Image Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
