BACKPROPAGATION USES PRIOR INFORMATION EFFICIENTLY

The ability of neural net classifiers to deal with a priori information is investigated. For this purpose, back-propagation classifiers are trained with data from known distributions with variable a priori probabilities, and their performance on separate test sets is evaluated. It is found that back-propagation employs a priori information in a slightly suboptimal fashion, but that this does not have serious consequences on the performance of this classifier. Furthermore, it is found that the inferior generalization that results when an excessive number of network parameters are used can (partially) be ascribed to this suboptimality.