ANN Tool in MATLAB

While using Neural network pattern recognition tool(nprtool) in matlab,(For classification after getting all features) first we have to give input data from the workspace as a database file and then it asks for target data defining the desired output. I can't understand that if,i give input the features_vector of an image,then from where can i get the target data_vector?I mean how to estimate the target_data for each feature..

Answer 1

[Greg Heath]

If there are c classes or categories and N examples of I-dimensional inputs.

 [ I N ] = size(input)
 [ c N  ] = size(target)

where the target matrix contains c-dimensional {0,1} unit vectors satisfying

 sum(target)           = ones(1,N)
 vec2ind(target)       = classindices
 ind2vec(classindices) = target

Look at the target vectors of the classification data examples in

 help nndatasets
 doc nndatasets

Hope this helps.

Thank you for formally accepting my answer

Greg

[Durga]

Thank u sir.

Answer 2

[Shoba Selvaraj]

In which form ANN receives a input?

[Durga]

In a form of n-dimensional input vector database file.