Neural-net classifiers and a priori information

Summary form only given, as follows. The ability of neural-net classifiers to deal with a priori information was investigated. For this purpose, backpropagation classifiers were trained with data from known distributions with variable a priori probabilities, and their performance on separate test sets was evaluated. It was found that backpropagation employs a priori information in a slightly suboptimal fashion, but that this does not have serious consequences for the performance of this classifier