In supervised training, the training patterns must be provided in input/teacher pattern pairs, , where M is the number of training pairs. Depending on the nature of the teacher's information, there are two approaches to supervised learning. One is based on the correctness of the decision and the other based on the optimization of a training cost criterion. Of the later, the least square error approximation based formulation represents the most important special case. The decision based and approximation based formulations differ in their teacher's information and the ways of utilizing it.
Artificial Neural Networks