| Summary: | 碩士 === 國立中興大學 === 應用數學研究所 === 82 === In the pattern classification problem, it is known that the
Bayes decision rule, which separates k classes, gives a minimum
probability of misclassification. In this study, the prior
probability of each class is unknown and the conditional
density functions are known. A set of unidentified input
patterns is used to establish an empirical Bayes rule, which
separates k classes and which leads to estimation of the
priors. This can adapt itself to a better decision rule by
making use of input patterns while the system is in use. The
resulting misclassification can be made arbitrarily close to
that of the rule. The result of a Monte Carlo Simulation study
with normal, uniform and exponential distributions are
presented to the favorable prior estimation for the empirical
Bayes rule.
|
|---|
