Abstract | ||
---|---|---|
Herein we investigate learning in the limit where confidence in the current conjecture accrues with time. Confidence levels are given by rational numbers between 0 and 1. The traditional requirement that for learning in the limit is that a device must converge (in the limit) to a correct answer. We further demand that the associated confidence in the answer (monotonically) approach 1 in the limit. In addition to being a more realistic model of learning, our new notion turns out to be a more powerful as well. In addition, we give precise characterizations of the classes of functions that are learnable in our new model(s). |
Year | DOI | Venue |
---|---|---|
1996 | 10.1007/3-540-60922-9_18 | STACS |
Keywords | Field | DocType |
confidence level,rational number | Inductive reasoning,Discrete mathematics,Monotonic function,Rational number,Computer science,Recursive functions,Conjecture | Conference |
ISBN | Citations | PageRank |
3-540-60922-9 | 8 | 0.63 |
References | Authors | |
7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Janis Barzdins | 1 | 199 | 35.69 |
Rusins Freivalds | 2 | 781 | 90.68 |
Carl H. Smith | 3 | 194 | 33.15 |