Neural Network cost function normalization
显示 更早的评论
Hello,
I am using feedforward network in MATLAB.
My question is "what is the definite procedure of Normalization?".
Code: net.performParam.normalization='percent';
In the help, "'percent', which normalizes errors between -1 and 1" is written.
Then does it mean that normalization makes minimum value of errors to -1, and maximum value to 1?
For example, ground truth data is "1 2 3 4"
and the NN's output is "0.9 1.95 3 4.1"
then the errors would be "-0.1, -0.05, 0, 0.1".
Then, after normalization, will it become "-1 -0.5 0 1"?
Thanks regard.
回答（1 个）
Sahil Jain
2021-8-13
0 个投票
The documentation for "nnparam.normalization" says "If it is set to 'percent' then percentage errors are used, relative to the ranges of the original target data, and errors will be mapped to the range [-1,1]."
Therefore, if "t" and "y" are the ground truth and output predictions respectively, then the normalized error values would be 
2 个评论
Dong Youn Lee
2021-8-13
少快 王
2024-1-2
Why is the range of the error not max(e) - min(e), but max(t)-min(t)? I think en(error normalization) should be：en=2*(e-min(e)) / (max(e) - min(e))-1
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
2021-8-9
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
