清空筛选条件
清空筛选条件

Neural Network Output :Scaling the output range.

9 次查看（过去 30 天）
Ashikur
Ashikur 2012-1-28
Hi,
The output layer of my neural network (3 layered) is using sigmoid as activation which outputs only in range [0-1]. However, if I want to train it for outputs that are beyond [0-1], say in thousands, what should I do?
For example if I want to train
input ----> output
0 0 ------> 0
0 1 ------> 1000
1000 1 ----> 1
1 1 -------> 0
My program works for AND, OR, XOR etc. As input output are all in binary.
There were some suggestion to use,
Activation:
-----------
y = lambda*(abs(x)*1/(1+exp(-1*(x))))
Derivative of activation:
-------------------------
lambda*(abs(y)*y*(1-y))
This did not converge for the mentioned training pattern. Are there any suggestion please?

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2012-1-31
Hello Greg,
Thanks again for answering the question. For my case, no rigid bound,
1. INCORRECT. ALL 3 VARIABLES ARE BOUNDED:
0 <= X1, Y <= 1000
0<= X2 <= 1.
2. HOWEVER, SINCE THE INPUT SCALES ARE DIFFERENT BY A FACTOR OF THOUSAND, X1 AND Y SHOULD BE TRANSFORMED BY VIA LOGS AND/OR POWERS. E.G.,
X1n = LOG10( 1 + X1 ) / LOG10( 1001 ) ==> 0 <= X1n <= 1
SIMILARLY FOR Y
HOPE THIS HELPS.
GREG

更多回答（1 个）

Greg Heath
Greg Heath 2012-1-29
If the target has rigid bounds, scale the data to either [0,1] or [-1,1] and use either LOGSIG or TANSIG, respectively.
Otherwise, standardize to zero-mean/unit variance and use PURELIN.
To recover the original data scale, just use the reverse tranformations.
Hope this helps.
Greg
  1 个评论
Ashikur
Ashikur 2012-1-29
Hello Greg,
Thanks again for answering the question. For my case, no rigid bound, So I will use purelin or f(x) = x
1. Standardize what? the input? each input vector individually? or the whole training input matrix?
2. Do I need to do the same standardization for desired output too?
I used purlin (f(x)=x) in my output, but it seems not to converge for,
0 0 ------> 0
0 1 ------> 1000
1000 1 ----> 1
1 1 -------> 0
The codes are in below link,
https://docs.google.com/document/d/18kGXAgeVP1kOlJHZJ2KmV_mkxY61f255LQjPcr6uwnI/edit?pli=1
https://docs.google.com/document/d/13YVWHUXug6XrngQD3a52IgzPxMH2M9sgECkb7peRckA/edit?pli=1
Hope you will have some times to see the problem.

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Define Shallow Neural Network Architectures 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by