sim function of the neuralnetwork

I want to simulate the network that I got with the new data and I use results=sim(net, new data) should I normalize the new data? and to get the real value of the result of network I need to denormalize the results? Thanks for any idea

Answer 1

[Mudambi Srivatsa]

With the new_data, you can use the following command to simulate the network

results = sim(net, new_data)

Further, you can use the trained network to predict as follows:

 output = net(new_data)

The following post might be helpful regarding the normalizing process:

https://www.mathworks.com/matlabcentral/answers/14590-neural-network-sim-net-input-gives-crazy-results

Answer 2

[Greg Heath]

No.

The net automatically normalizes the input with mapminmax and denormalizes the output with the inverse.

Hope this helps

Thank you for formally accepting my answer

Greg

[Rita]

Thanks, Greg.I have not used mapminmax function.I just used newff and configure functions.But I have normalized the data manually before entering the network. So do I still need to normalize the new data and then simulate by the network?

Answer 3

[Greg Heath]

1. You didn't specify if this is

   a. regression/curve-fitting (FITNET OR NEWFIT)
or 
   b. classification/pattern-recognition (PATTERNNET or NEWPR)

The current functions FITNET and PATTERNET are special cases of FEEDFORWARDNET whereas the obsolete functions NEWFIT and NEWPR are special cases of the obsolete function NEWFF.

2. In either case the DEFAULT is to automatically normalize inputs and de-normalize outputs with MAPMINMAX.

3. However, there are options to use either

 a. MAPSTD

or

 b. No normalization/de-normalization.

So, IT DEPENDS WHAT THE PROGRAM AUTHOR USED.

4. Personally, I prefer to

 a. Use MAPSTD BEFORE THE NET for detecting outliers so I can 
   either modify or remove them.
 b. Accept the default MAPMINMAX because I am too lazy to remove 
    it.

BOTTOM LINE: Your input should have the same summary statistics as the author's data. Then the net will automatically do the rest.

Hope this helps

Thank you for formally accepting my answer

Greg