Supervised
Models
Supervised learning networks represent the main stream of the development
in neural networks. Some examples of well known pioneering networks include
the perceptron network, ADALINE/MADALINE,
and various multilayer networks. Two phases are involved in a supervised
learning network: retrieving
phase and learning phase.
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.
Decision Based Neural Networks
Contents
Artificial Neural Networks
About this Tutorial