E. Fast Training Program;
 1. Purpose;
   a. Initialize a MLP using random initial weights
   b. Train a MLP network using HWO_OWO. a method much faster than BP
 
 2. Features;

   a. Uses a batching approach, so the order of training 
      patterns is unimportant
   b. Has adaptive learning factor
   c. Shows training MSE
   
 3. Example

 twod.tra              ! filename for training data 
 8                     ! number of inputs
 7                     ! number of outputs
 7                     ! number of hidden units
 15                    ! number of iterations


      The program will read all patterns from the file twod.tra, and 
      train a MLP using the following network structure which is
      shown below.
          
           8          7         7
     
      The network will have 3 layers including 8 inputs, 7 hidden units
      in one hidden layer, and 7 outputs. In addition, layers 2 and
      3 connect to all previous layers. Training will stop
      after 15 iterations.
  
    You can run this program on your own data.


