 

  Self-Organizing Map Comments 
 
  1. Cluster a data file using Kohonen's Self-Organizing 
     Feature Map.
  2. Plots a 2-D projection of the clusters and the clustering error 
     versus iteration number. 

  Input details
 
  1.Choose the training file from the training data folder.
  2.Choose the total number of columns in the training file.
  3.Choose the number of columns to be classified(number of inputs).
  4.Choose the number of clusters.
  5.Choose the number of iterations.

 Example:

  TWOD.TRA ! training file
  15       ! totoal number of columns
  8  	   ! number of inputs 
  20	   ! number of clusters
  20	   ! number of iteratioons

     we see that the program will apply Self-Organizing Map clustering
     to the file Twod.tra with 20 iterations. The number of random initial 
     clusters is 20. The initial learning factor and half-neighborhood
     size are respectively .04 and 3.25, and linearly decreasing neighborhoods 
     and learning factor are chosen. The clusters will be saved in a file.
     After running the program, we can observe that the normalized clustering error is 4.964849.
     You can run this program on your own data.
