Neural network technology was compared with simultaneous and stepwise linear discriminant analysis in terms of their ability to classify and predict persons (n=138) as having autism or mental retardation. The neural network methodology was superior in both classifying groups and in generalizing to new cases that were not part of the training…

Forty-eight children (ages 5 to 13) with autism or related pervasive developmental disability were paired with normally developing peers for informal play periods. Compared to a control group, the experimental children demonstrated improved social behavior which sometimes generalized to interactions with other children and the larger school…