B. Getting Started
  1. Processing Examples
     An example run can be made for each processing option in 
     this package, using the data files in directory 
     \trainingdata. These processing examples are run as follows.
   a. From Windows EXplorer or from the Start Menu on the Task Bar 
      run NNMap.exe.
   b. You will see the Neural Networks for Mapping pull down menu.
   c. Go to the option you are interested in. However, 
      it is better to start with utilities.
   d. Choose a training data.
   e. Examine the training data by calculating
      the mean and the standard deviation.Also plot the columns
      and their respective histograms to check for bad patterns.
   f. Feature selection is done to choose the most important pattern 
      and delete the useless patterns if needed.
   g. Go to the options and choose fast training under MLP submenu
      to train a big network.
      PLN can also be used to train a big network.
   h. The trained network is pruned by choosing the MLP pruning submenu.
   i. After pruning,one of the network is choosen for fast training.
   j. The trained network is tested by choosing the MLP testing submenu.
   k. The trained network can also be processed by choosing the
      MLP processing submenu.
   l. The training data can also be examined by Kmean and SOM for classification.
   m. The examined patterns can be classified by choosing one of the 
      classification submenus like KMean,SOM,classify vector under the
      unsupervised learning menu.


