Confident and Consistent Partial Learning of Recursive Functions
| dc.contributor.author | GAO, Ziyuan | en_US |
| dc.contributor.author | STEPHAN, Frank | en_US |
| dc.date.accessioned | 2014-07-15T06:52:54Z | en_US |
| dc.date.accessioned | 2017-01-23T06:59:42Z | |
| dc.date.available | 2014-07-15T06:52:54Z | en_US |
| dc.date.available | 2017-01-23T06:59:42Z | |
| dc.date.issued | 2014-07-10 | en_US |
| dc.description.abstract | Partial learning is a criterion where the learner in nitely often outputs one correct conjecture while every other hypothesis is issued only nitely often. This paper addresses two variants of partial learning in the setting of inductive inference of functions: rst, con dent partial learning requires that the learner also on those functions which it does not learn, singles out exactly one hypothesis which is output in nitely often; second, essentially class consistent partial learning is partial learning with the additional constraint that on the functions to be learnt, almost all hypothe- ses issued are consistent with all the data seen so far. The results of the present work are that con dent partial learning is more general than explanatory learning, incom- parable with behaviourally correct learning and closed under union; essentially class consistent partial learning is more general than behaviourally correct learning and incomparable with con dent partial learning. Furthermore, it is investigated which oracles permit to learn all recursive functions under these criteria: for con dent par- tial learning, some non-high oracles are omniscient; for essentially class consistent partial learning, all PA-complete and all oracles of hyperimmune Turing degree are omniscient. | en_US |
| dc.identifier.uri | https://dl.comp.nus.edu.sg/xmlui/handle/1900.100/4664 | en_US |
| dc.language.iso | en | en_US |
| dc.relation.ispartofseries | TRB7/14; | en_US |
| dc.title | Confident and Consistent Partial Learning of Recursive Functions | en_US |
| dc.type | Technical Report | en_US |