MATLAB Answers


Normalizing data for neural networks

Asked by John
on 10 Jan 2012
Latest activity Commented on by electronx engr on 4 Nov 2017


I've read that it is good practice to normalize data before training a neural network.

There are different ways of normalizing data.

Does the data have to me normalized between 0 and 1? or can it be done using the standardize function - which won't necessarily give you numbers between 0 and 1 and could give you negative numbers.

Many thanks


Log in to comment.

5 Answers

Answer by Chandra Kurniawan on 10 Jan 2012
 Accepted Answer


I've heard that the artificial neural network training data must be normalized before the training process.

I have a code that can normalize your data into spesific range that you want.

p = [4 4 3 3 4;            
     2 1 2 1 1;
     2 2 2 4 2];
a = min(p(:));
b = max(p(:));
ra = 0.9;
rb = 0.1;
pa = (((ra-rb) * (p - a)) / (b - a)) + rb;

Let say you want to normalize p into 0.1 to 0.9.

p is your data.

ra is 0.9 and rb is 0.1.

Then your normalized data is pa


Demos in the comp.a.neural-nets FAQ indicate that better precision is obtained when the input data is relatively balanced about 0 AND TANSIG (instead of LOGSIG) activation functions are used in hidden layers.

Hope this helps.


i want to find out my output in original form how can i find it ? please help me

If you use the standard programs e.g., FITNET, PATTERNNET, TIMEDELAYNET, NARNET & NARXNET,

All of the normalization and de-normalization is done automatically (==>DONWORRIBOUTIT).

All you have to do is run the example programs in, e.g.,

 help fitnet
 doc fitnet

If you need additional sample data

 help nndatasets
 doc nndatasets

For more detailed examples search in the NEWSGROUP and ANSWERS. For example

 NEWSGROUP              2014-15     all-time
 tutorial                  58         2575
 tutorial neural           16          127
 tutorial neural greg      15           58

Hope this helps.


Log in to comment.

Answer by Greg Heath
on 11 Jan 2012

The best combination to use for a MLP (e.g., NEWFF) with one or more hidden layers is

1. TANSIG hidden layer activation functions

2. EITHER standardization (zero-mean/unit-variance: doc MAPSTD)

   OR [ -1 1 ] normalization ( [min,max] => [ -1, 1 ] ): doc MAPMINMAX)

Convincing demonstrations are available in the FAQ.

For classification among c classes, using columns of the c-dimensional unit matrix eye(c) as targets guarantees that the outputs can be interpreted as valid approximatations to input conditional posterior probabilities. For that reason, the commonly used normalization to [0.1 0.9] is not recommended.

WARNING: NEWFF automatically uses the MINMAX normalization as a default. Standardization must be explicitly specified.

Hope this helps.



Show 1 older comment

I dont have access to the Neural Network Toolbox anymore, but if I recall correctly you should be able to generate code from the nprtool GUI (last tab maybe?). You can use this code to do your work without the GUI, customize it as need be, and also learn from it to gain a deeper understanding.

What I think Greg is referring to above is the fact that the function "newff" (a quick function to initialize a network) uses the built in normalization (see toolbox function mapminmax). If you want to change this, you'll have to make some custom changes. I dont recall if the nprtool uses newff - this can be verified by generating and viewing the code.

This is all from memory as I dont have access to the toolbox anymore - so take my comments as general guidelines, not as absolute.

Good luck.

Thank you

Standardization means zero-mean/unit-variance.

My preferences:

1. TANSIG in hidden layers

2. Standardize reals and mixtures of reals and binary.

3. {-1,1} for binary and reals that have bounds imposed by math or physics.

Hope this helps.


Log in to comment.

Answer by Greg Heath
on 14 Jan 2012

In general, if you decide to standardize or normalize, each ROW is treated SEPARATELY.

If you do this, either use MAPSTD, MAPMNMX, or the following:

[I N] = size(p)


meanp = repmat(mean(p,2),1,N);

stdp = repmat(std(p,0,2),1,N);

pstd = (p-meanp)./stdp ;


minp = repmat(min(p,[],2),1,N);

maxp = repmat(max(p,[],2),1,N);

pn = minpn +(maxpn-minpn).*(p-minp)./(maxp-pmin);

Hope this helps



Show 1 older comment

hi, Undefined function or variable 'pmin'.

Yeah, should be minp.

plz can u help me in this that after training with normalized data, how can I get the network (using gensim command) that works on unnormalized input, since I have created and trained the network using normalized input and output?

Log in to comment.

Answer by Sarillee
on 25 Mar 2013


try this...

x is input....

y is the output...

  1 Comment

Not valid for matrix inputs

Log in to comment.

Answer by Imran Babar on 8 May 2013

mu_input=mean(trainingInput); std_input=std(trainingInput); trainingInput=(trainingInput(:,:)-mu_input(:,1))/std_input(:,1);

I hope this will serve your purpose


Not valid for matrix inputs

in case of matrix data, the min and max value corresponds to a column or the whole dataset. E.g. i have 5 input columns of data, in this case whether i should choose min/max for each column and do the normalization or min/max form all over the column and calculate.

Log in to comment.

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Win prizes and improve your MATLAB skills

Play today