Title :
The multilayer perceptron as an approximation to a Bayes optimal discriminant function
Author :
Ruck, Dennis W. ; Rogers, Steven K. ; Kabrisky, Matthew ; Oxley, Mark E. ; Suter, Bruce W.
Author_Institution :
Sch. of Eng., US Air Force Inst. of Technol., Wright-Patterson AFB, OH, USA
fDate :
12/1/1990 12:00:00 AM
Abstract :
The multilayer perceptron, when trained as a classifier using backpropagation, is shown to approximate the Bayes optimal discriminant function. The result is demonstrated for both the two-class problem and multiple classes. It is shown that the outputs of the multilayer perceptron approximate the a posteriori probability functions of the classes being trained. The proof applies to any number of layers and any type of unit activation function, linear or nonlinear
Keywords :
neural nets; probability; Bayes optimal discriminant function; backpropagation; classifier; multilayer perceptron; multiple class problems; neural networks; probability; two-class problem; unit activation function; Backpropagation; Bayesian methods; Books; Image analysis; Multi-layer neural network; Multilayer perceptrons; Neural networks; Pattern recognition; Probability density function;
Journal_Title :
Neural Networks, IEEE Transactions on
