Receiver operating characteristics of perceptrons: Influence of sample size and prevalence

In many practical classification problems it is important to distinguish fa lse positive from false negative results when evaluating the performance of the classifier. This is of particular importance for medical diagnostic te sts. In this context, receiver operating characteristic (ROC) curves have b ecome a standard tool. Here we apply this concept to characterize the perfo rmance of a simple neural network. Investigating the binary classification of a perceptron we calculate analytically the shape of the corresponding RO C curves. The influence of die size of the training set and the prevalence of the quality considered are studied by means of a statistical-mechanics a nalysis. [S1063-651X(99)06911-1].