Bayes theorem is a principled way to calculate posterior
probability of each hypothesis
Assumptions: The training data is noise free (i.e., ). The target
concept is contained in . We have no a priori reason to believe
that any hypothesis is more probable than any other.
). The target
concept is contained in 
. We have no a priori reason to believe
that any hypothesis is more probable than any other.
for all 
in 
, 
