Title :
A note on learning for Gaussian properties
Author :
Keehn, Daniel G.
fDate :
1/1/1965 12:00:00 AM
Abstract :
By employing a Bayesian approach to the analysis of learning the probability distribution of property vectors, an estimation likelihood computation scheme for the general Gaussian distribution (quadratic adaptive decision surface) is shown optimum. Some results relating the number of learning samples to Type I misclassification errors are included.
Keywords :
Bayes procedures; Gaussian processes; Learning procedures; Pattern classification; Bayesian methods; Distributed computing; Gaussian distribution; Nominations and elections; Pattern recognition; Probability distribution; Q measurement; Space technology; Statistical analysis; Surface treatment;
Journal_Title :
Information Theory, IEEE Transactions on
DOI :
10.1109/TIT.1965.1053726
