I have some concerns related to the use of nntool in MATLAB toolbox. Following links like this, I have found that nntool by default normalizes the inputs to the range [-1 1]. So I am a bit concerned, I created a neural network with tansig activation in the first layer and logsig activation in the output layer. I manually normalized the outputs to the range of [0 1] in the data and fed it to nntool.

Now my question is does nntool further normalizes it to the range [-1 1]. If it does then it is not correct, the output of logsig cannot be in the range of [-1 1].

I am using the newfit function like this

load house_dataset;
net = newfit(houseInputs,houseTargets,20);

Any suggestions?


closed as off-topic by kjetil b halvorsen, Michael Chernick, Siong Thye Goh, user158565, jpmuc Jun 5 at 8:21

This question appears to be off-topic. The users who voted to close gave this specific reason:

  • "This question appears to be off-topic because EITHER it is not about statistics, machine learning, data analysis, data mining, or data visualization, OR it focuses on programming, debugging, or performing routine operations within a statistical computing platform. If the latter, you could try the support links we maintain." – kjetil b halvorsen, Michael Chernick, Siong Thye Goh, user158565, jpmuc
If this question can be reworded to fit the rules in the help center, please edit the question.


nntool has a large number of tunable parameters, refer to the documentation for more details. In particular section Preprocessing and Postprocessing deals with different types of pre- and postprocessing techniques which are available in the toolbox.

When you look at the newfit definition you can find such information:

Purpose Create fitting network

Syntax net = newfit(P,T,S,TF,BTF,BLF,PF,IPF,OPF,DDF)

Description newfit(P,T,S,TF,BTF,BLF,PF,IPF,OPF,DDF) takes the following:


IPF Row cell array of input processing functions. Default is {'fixunknowns','remconstantrows','mapminmax'}.

OPF Row cell array of output processing functions. Default is {'remconstantrows','mapminmax'}


So you can simply change them to IPF={'fixunknowns','remconstantrows'} and OPF={'remconstantrows'} to turn the min-max mapping off.


Not the answer you're looking for? Browse other questions tagged or ask your own question.