MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

# Normalizing data for neural networks

Asked by John on 10 Jan 2012
Latest activity Commented on by Abul Fujail on 12 Dec 2013

Hi,

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

## Products

No products are associated with this question.

Answer by Chandra Kurniawan on 10 Jan 2012

Hi,

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.

ra is 0.9 and rb is 0.1.

Then your normalized data is pa

## 1 Comment

Greg Heath on 11 Jan 2012

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.

Greg

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 comp.ai.neural-nets 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.

Greg

owr on 11 Jan 2012

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.

John on 12 Jan 2012

Thank you

Greg Heath on 13 Jan 2012

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.

Greg

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)

%STANDARDIZATION

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

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

pstd = (p-meanp)./stdp ;

%NORMALIZATION

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

Greg

## 1 Comment

John on 16 Jan 2012

Many thanks

Answer by Sarillee on 25 Mar 2013

y=(x-min(x))/(max(x)-min(x))

try this...

x is input....

y is the output...

## 1 Comment

Greg Heath on 10 May 2013

Not valid for matrix inputs

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