|
CAP 5605 Artificial Intelligence Chris Lacher Stanford CF Algebra |
Stanford Certainty factor Algebra
For a hypothesis (or rule) H:
- Definitions:
MB(H|E) = measure of belief in H given evidence E
MD(H|E) = measure of disbelief in H given evidence E- Assumptions:
(1 >= MB(H|E) >= 0) and (MD(H|E) == 0) OR (1 >= MD(H|E) >= 0) and (MB(H|E) == 0)
- Definition:
CF(H|E) = MB(H|E) - MD(H|E)
Combining Certainty Factors:
- Dynamic Certainty for a Conclusion:
Given a rule R = "if H then C with certainty CF(R)" and a calculated certainty CF(H),
CF(C) = CF(H) x CF(R)- Conjunction and Disjunction of Hypotheses:
CF (P1 and P2) = MIN { CF(P1) , CF(P2) }
CF (P1 or P2) = MAX { CF(P1) , CF(P2) }- Multiple Rules with Same Conclusion:
Suppose we have two rules R1 and R2 with the same conclusion C,
CF(C) = CF(R1) + CF(R2) - (CF(R1) x CF(R2)), when both CF(R1) and CF(R2) are positive
CF(C) = CF(R1) + CF(R2) + (CF(R1) x CF(R2)), when both CF(R1) and CF(R2) are negative
(CF(R1) + CF(R2)) / (1 - MIN { |CF(R1)| , |CF(R2)| }), when the signs are different
Example:
Rule Base -------- R1: if a and b then x (cf = 0.5) R2: if c or d then x (cf = 0.7) Dynamic Input: ------------- a, with certainty 1.0 b, with certainty 0.8 c, with certainty 0.9 d, with certainty 0.7 Compute CF values for x: ----------------------- CF(a and b) = MIN{1.0, 0.8} = 0.8 ==> CF1(x) = 0.8 * 0.5 = 0.4 CF(c or d) = MAX{0.9, 0.7} = 0.9 ==> CF2(x) = 0.9 * 0.7 = 0.63 CF(x) = 0.4 + 0.63 - 0.4*0.63 = 0.778
Closed Form