1. sources of uncertainty in rules
   1. related to individual rules
      1. Antecedent
         1. Errors
         2. Likelihood of Evidence
         3. Combining of Evidence
      2. consequent
         1. Errors
         2. Likelihood of Evidence
   2. due to conflict resolution
      1. contradiction of rules
      2. subsumption of rules
      3. redundancy of rules
      4. missing rules
      5. data fusion
   3. due to incompatibility of rules
      1. explicit priority of rules
      2. implicit priority of rules
         1. speciality of patterns
         2. recency of facts matching patterns
         3. ordering of patterns
            1. lexicographic "lex"
            2. Means -Ends Analysis "MEA"
         4. order that rules entered
2. methods for dealing with uncertainty
   1. Ad Hoc Methods
   2. Certainty Factors
      1. Positive CF – evidence supports the hypothesis
      2. CF = 1 – evidence definitely proves the hypothesis
      3. CF = 0 – there is no evidence
      4. Negative CF – evidence favors negation of the hypothesis
      5. simple to implement where inference chains are short
      6. not generally valid for longer inference chains
   3. Bayesian diffculties
      1. determining the probabilities of givens – symptoms / analyses.
      2. Evidence tends to accumulate over time.
   4. Belief and Disbelief
      1. P(H|E) = 1 – P(H’|E), E evidence
3. Dempster-Shafer theory
   1. a fixed set of mutually exclusive & exhaustive elements called environment  = {1, 2, …, N}
4. theory of uncertainty based on fuzzy logic
   1. has wide applicability due to the extension principle.
   2. Approximate Reasoning
      1. theory of uncertainty based on fuzzy logic and concerned with quantifying and reasoning using natural language
   3. possibility refers to allowed values.
   4. probability distributions – frequency of expected occurrence of some random variable.
   5. A discrimination function is a way to represent which objects are members of a set.
5. Verification vs. Validation
   1. Verification minimizing the local uncertainties.
   2. Validation minimizing the global uncertainties