Neural network Bayes error estimation

A neural network approach to obtaining upper and lower bounds on the Bayes error rate for pattern recognition problems is presented. The approach is developed using the key concept of resubstitution and leave-one-out testing from conventional nonparametric error estimation techniques. The neural network approach is evaluated by applying it to several eight-dimensional, two-class “toy” problems, where the Bayes error rate is known. The upper bound of the Bayes error rate is reliably found for problems with complex decision boundary surfaces. Alternative testing approaches are suggested for reducing the difference between the bounds and the true Bayes rate