File:       examples/ex_alpha.pl
        Author: Josiah Bryan, <jdb@wcoil.com>
        Desc: 

                This demonstrates the ability of a neural net to 
                generalize and predict what the correct result is 
                for inputs that it has never seen before.
                
                This teaches the network to classify some twenty-
                nine seperate 35-byte bitmaps, and then it inputs
                an never-before-seen bitmap and displays the 
                classification the network gives for the unknown bitmap.