A critical overview of neural network pattern classifiers

Abstract

A taxonomy of neural network pattern classifiers is presented which includes four major groupings. Global discriminant classifiers use sigmoid or polynomial computing elements that have 'high' nonzero outputs over most of their input space. Local discriminant classifiers use Gaussian or other localized computing elements that have 'high' nonzero outputs over only a small localized region of their input space. Nearest neighbor classifiers compute the distance to stored exemplar patterns and rule forming classifiers use binary threshold-logic computing elements to produce binary outputs. Results of experiments are presented which demonstrate that neural network classifiers provide error rates which are equivalent to and sometimes lower than those of more conventional Gaussian. Gaussian mixture, and binary three classifiers using the same amount of training data.<>