The handling of don´t care attributes

A critical factor that affects the performance of neural network training algorithms and the generalization of trained networks is the training instances. The authors consider the handling of don´t care attributes in training instances. Several approaches are discussed and their experimental results are presented. The following approaches are considered: (1) replace don´t care attributes with a fixed value; (2) replace don´t care attributes with their maximum or minimum encoded values; (3) replace don´t care attributes with their maximum and minimum encoded values; and (4) replace don´t care attributes with all their possible encoded values