Ee 5322: Intelligent Control Systems

Probability theory has been traditionally used to characterize both types of uncertainty. E.g. aleatory uncertainty can be best dealt with using the frequentist approach associated with traditional probability theory. However, probability theory is not capable of completely capturing epistemic uncertainty. The traditional method was called Bayesian Probability. In this method, it is necessary to have information on the probability of all the events. When this is not available, uniform distribution function is often used, which means that all simple events for which a probability distribution is not known in a given sample space are equally likely. An additional assumption in the classical probability is the axiom of additivity where all probabilities that satisfy specific properties must add to 1.