Expert Systems: Uncertainty Management Flashcards
Examples of a source of uncertainty
Weak implications, Imprecise language, Unknown data, Combining the views of different experts
The difference between probability and fuzzy membership in measuring uncertainty
The probability of an event is the proportion of cases in which the event occurs. It’s a scientific measure of chance. It can be expressed mathematically as a numerical index with a range between 0 to unity. Fuzzy logic is determined as a set of mathematical principles for knowledge representation based on the degree of membership rather than on crisp membership of classical binary logic
What is uncertainty in AI?
The lack of exact knowledge that would enable us to reach a perfectly reliable solution
Weak implications as a source of uncertainty
They are vague associations between IF and THEN parts of the rules.
Examples of weak implications
If there are any certainty factors to indicate a degree of correlation or if there are any further reasoning based on the fact stated
Imprecise language as a source of uncertainty
There are various ways to express knowledge in the precise IF-THEN form of rules
Unknown data as a source of uncertainty
When data are incomplete or missing, the only solution is to accept the value “unknown” and proceed to an approximate reasoning with this value
Combining views as a source of uncertainty
Experts often have contradictory opinions and produce conflicting rules. To resolve the conflict, one has to attach a weight to each expert and then calculate the composite conclusion. No systematic method exists to obtain weights. Experts will reach exactly the same conclusions
How to calculate the probability of success?
The number of successes / The number of possible outcomes
How to calculate the probability of failure?
The number of failures / The number of possible outcomes
Crisp set (logic) vs Fuzzy set (logic)
Crisp set defines value either 1 or 0. It is also called a classical set and it shows full membership meaning true/false, yes/no, 0/1. Fuzzy set defines values between 0 and 1. It specifies the degree to which something is true and it shows partial membership meaning true to false, yes to no, 0 to 1