I am using nctool of MATLAB and want to tag different input vectors in such a manner so that I can recognize their position even after their entry in SOM (self organizing maps).
Dear Friend, for clustering problems, the self-organizing feature map (SOM) is the most commonly used network, because after the network has been trained, there are many visualization tools that can be used to analyze the resulting clusters. This network has one layer, with neurons organized in a grid. (For more information on the SOM, see "Self-Organizing Feature Maps" in the User's Guide http://www.mathworks.in/help/toolbox/nnet/gs/f9-27151.html) When creating the network, you specify the numbers of rows and columns in the grid. Here, the number of rows and columns is set to 10. The total number of neurons is 100. You can change this number in another run if you want.
Export "output" matrix in the workspace. The "output" matrix gives associates each input vector with one position on the SOM graph. You can extract the information from there.
Personally i don't use SOMs because they are dfficult to interpret. I prefer Fuzzy clustering or probabilistic fuzzy clustering.
or you can auto exchange the matlab output file data ...between Matlab and MS Excel ...How to do it? go to google seach tutorial Matlab ans Ms Excel file data exchange ....