Abstract | ||
---|---|---|
Several well-known inductive inference strategies change the actual hypothesis only when they discover that it provably misclassifies an example seen so far. This notion is made mathematically precise and its general power is characterized. In spite of its strength it is shown that this approach is not of universal power. Consequently, then hypotheses are considered which unprovably misclassify examples and the properties of this approach are studied. Among others it turns out that this type is of the same power as monotonic identification. Finally, it is shown that universal power can be achieved only when an unbounded number of alternations of these dual types of hypotheses is allowed. |
Year | DOI | Venue |
---|---|---|
1991 | 10.1007/BFb0030395 | Nonmonotonic and Inductive Logic |
Keywords | Field | DocType |
dual types,inductive inference | Monotonic function,Inductive reasoning,Computer science,Algorithm,Initial segment,Recursive functions,Spite | Conference |
ISBN | Citations | PageRank |
3-540-56433-0 | 0 | 0.34 |
References | Authors | |
14 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rusins Freivalds | 1 | 781 | 90.68 |
Efim Kinber | 2 | 421 | 44.95 |
Rolf Wiehagen | 3 | 835 | 105.73 |