A confidence model for finite-memory learning systems (Corresp.)
J. Horos, Martin E. Hellman · IEEE Transactions on Information Theory · 1972
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.