neural network nprtool tansig vs logsig

4 Ansichten (letzte 30 Tage)
Cagdas Ozgenc
Cagdas Ozgenc am 14 Apr. 2013
Hello,
I am a little confused about the nprtool in the neural network toolbox. It generates a two layer feedforward network with a tansig activation on the output layer. However it expects a binary output with {0,1} and it seems to work right.
I wonder why doesn't it use logsig activation if the output will be {0,1}. When I manually modify the output activation to logsig the generated output gets compressed to [0.5,1] range, which is wrong.
I can't explain what seems to be the problem.
Thanks

Akzeptierte Antwort

Greg Heath
Greg Heath am 1 Mai 2013
Most of the nets have a default mapminmax processing default that transforms outputs to the range (-1,1). For that range tansig is appropriate. There also is a default reverse transformation that yields the original target range.
My guess is that when you imposed 'logsig' the processing got screwed up.
Exactly what commands did you use to switch to 'logsig'?
Hope this helps.
*Thank you for formally accepting my answer.
Greg

Weitere Antworten (2)

Greg Heath
Greg Heath am 15 Apr. 2013
Bearbeitet: Greg Heath am 15 Apr. 2013
You can not manually add logsig after being trained with purelin
logsig(0:1) = 0.5 0.7311
The net has to be trained with logsig.
Hope this helps.
Thank you for formally accepting my answer
Greg
  2 Kommentare
Cagdas Ozgenc
Cagdas Ozgenc am 28 Apr. 2013
No I train with logsig by generating a script first from nprtool and modifying the activation function before running the script.
Greg Heath
Greg Heath am 29 Apr. 2013
Please post the script , initial RNG state, and the results from using one of the MATLAB classification nndatasets.

Melden Sie sich an, um zu kommentieren.


Vito
Vito am 29 Apr. 2013
This Fuzzy logic. AND = min(a,b), OR=max(a,b). The binary operator S can represent the addition(OR) boundary: S(1, 1) = 1, S(a, 0) = S(0, a) = a (logsig)
  2 Kommentare
Greg Heath
Greg Heath am 29 Apr. 2013
Wha??
Vito
Vito am 17 Mai 2013
Look at the theory, since classical logic, three-value and more fuzzy logic. The base of fuzzy logic is the algebra of Minima and Maxima which has the same properties, as Boolean algebra. In the help of ML about it it is told in general.

Melden Sie sich an, um zu kommentieren.

Community Treasure Hunt

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

Start Hunting!

Translated by