Title :
A confidence model for finite-memory learning systems (Corresp.)
Author :
Horos, John A. ; Hellman, Martin E.
fDate :
11/1/1972 12:00:00 AM
Abstract :
A confidence model for finite-memory learning systems is advanced in this correspondence. The primary difference between this and the previously used probability-of-error model is that a measure of confidence is associated with each decision and any incorrect decisions are weighted according to their confidence measure in figuring total loss. The optimal rule for this model is deterministic, whereas the previous model required randomized rules to achieve minimum error probability.
Keywords :
Finite-memory methods; Hypothesis testing; Learning procedures; Algebra; Equations; Error probability; Learning systems; Loss measurement; Matrices; Probability density function; Random variables; Statistics; Testing;
Journal_Title :
Information Theory, IEEE Transactions on
DOI :
10.1109/TIT.1972.1054918