No open-access location is known for this record yet.
No open-access location is known for this record yet.
One common feature of most knowledge-based expert systems is that they must reason based upon evidential information. Yet there is very little agreement on how this should be done. The authors present their current understanding of this problem and some partial solutions. They begin by characterizing evidence as a body of information that is uncertain, incomplete, and sometimes inaccurate. Based on this characterization, the authors conclude that evidential reasoning requires both a method for pooling multiple bodies of evidence to arrive at consensus opinion and some means of drawing the appropriate conclusions from that opinion. This approach, based on a relatively new mathematical theory of evidence, is contrasted with those approaches based on Bayesian probability models. The authors believe that their approach has some significant advantages, particularly its ability to represent and reason from bounded ignorance. 5 references.
Loading…
Imported from OpenAlex (CC0) — nothing here is generated.