Training Algorithm 
The relation of an original pattern P and it sunpatterns p1, p2, ...p16 is defined by P=(p1,p2,..pi,..p16) and for each pi , pi=(pi1,pi2,.. pik,..pi16) , ?pik={0,1}, where pik is the graylevel of a pixel. The value 1 indicates that the corresponding pixel is black, while the value 0 indicates that the corresponding pixel is white. For each vector pi, there exists a weight vector wi=(wi1,wi2,.. wik,..wi16) and a threshold  calculated by the equations wik=2 pik - 1  . These weight vectors are produced for remembering the training patterns in training phase. The threshold value  will inhibit the neuron‘s firing for all input vectors pjpi .That is . However, it is possible defining a reliable range in order to increase the tolerance of noisy. By experience, we take .

The proposed neural networks are guaranteed to converge in a single sweep. It provide a short time dealing with the training phase, the same result was seen during the identification phase.
 

nextindexback