Premium
Comments on An inquiry into computer understanding by Peter Cheeseman
Author(s) -
Dalkey N. C.
Publication year - 1988
Publication title -
computational intelligence
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.353
H-Index - 52
eISSN - 1467-8640
pISSN - 0824-7935
DOI - 10.1111/j.1467-8640.1988.tb00094.x
Subject(s) - citation , computer science , information retrieval , library science , world wide web , artificial intelligence
Suppose we have associated probabilities with Q and R. To make any logic, containing this rule, proof functional, we must be able to calculate the probability of Q&R.’ Unfortunately, this cannot be done without further information about the dependencies between Q and R. For instance, if Q and R both have. probabilities of % then the probability of Q&R could take any value between 0 and %. To see this, consider the cases R is -Q and R is Q. Cheeseman would represent these 3 probabilities by P(Qlc), P(Rlc), and P(Q&Rlc), where c is the conjunction of the axioms and hypotheses. He does not give any algorithm for calculating the third from the first and second. Bayes Theorem gives the relationship: