Matches in SemOpenAlex for { <https://semopenalex.org/work/W2271037598> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2271037598 abstract "Important refinements of concept learning in the limit from positive data considerably restricting the accessibility of input data are studied. Let c be any concept; every infinite sequence of elements exhausting c is called positive presentation of c. In all learning models considered the learning machine computes a sequence of hypotheses about the target concept from a positive presentation of it. With iterative learning, the learning machine, in making a conjecture, has access to its previous conjecture and the latest data items coming in. In k-bounded example-memory inference (k is a priori fixed) the learner is allowed to access, in making a conjecture, its previous hypothesis, its memory of up to k data items it has already seen, and the next element coming in. In the case of k-feedback identification, the learning machine, in making a conjecture, has access to its previous conjecture, the latest data item coming in, and, on the basis of this information, it can compute k items and query the database of previous data to find out, for each of the k items, whether or not it is in the database (k is again a priori fixed). In all cases, the sequence of conjectures has to converge to a hypothesis correctly describing the target concept. Our results are manyfold. An infinite hierarchy of more and more powerful feedback learners in dependence on the number k of queries allowed to be asked is established. However, the hierarchy collapses to 1-feedback inference if only indexed families of infinite concepts are considered, and moreover, its learning power is then equal to learning in the limit. But it remains infinite for concept classes of only infinite r.e. concepts. Both k-feedback inference and k-bounded example-memory identification are more powerful than iterative learning but incomparable to one another. Furthermore, there are cases where redundancy in the hypothesis space is shown to be a resource increasing the learning power of iterative learners. Finally, the union of at most k pattern languages is shown to be iteratively inferable." @default.
- W2271037598 created "2016-06-24" @default.
- W2271037598 creator A5033626728 @default.
- W2271037598 creator A5050068098 @default.
- W2271037598 creator A5050794957 @default.
- W2271037598 creator A5064075618 @default.
- W2271037598 date "1997-04-16" @default.
- W2271037598 modified "2023-09-27" @default.
- W2271037598 title "Incremental Concept Learning for Bounded Data Mining" @default.
- W2271037598 hasPublicationYear "1997" @default.
- W2271037598 type Work @default.
- W2271037598 sameAs 2271037598 @default.
- W2271037598 citedByCount "0" @default.
- W2271037598 crossrefType "journal-article" @default.
- W2271037598 hasAuthorship W2271037598A5033626728 @default.
- W2271037598 hasAuthorship W2271037598A5050068098 @default.
- W2271037598 hasAuthorship W2271037598A5050794957 @default.
- W2271037598 hasAuthorship W2271037598A5064075618 @default.
- W2271037598 hasConcept C111472728 @default.
- W2271037598 hasConcept C118615104 @default.
- W2271037598 hasConcept C119857082 @default.
- W2271037598 hasConcept C134306372 @default.
- W2271037598 hasConcept C138885662 @default.
- W2271037598 hasConcept C154945302 @default.
- W2271037598 hasConcept C162324750 @default.
- W2271037598 hasConcept C2776214188 @default.
- W2271037598 hasConcept C2778112365 @default.
- W2271037598 hasConcept C2780990831 @default.
- W2271037598 hasConcept C31170391 @default.
- W2271037598 hasConcept C33923547 @default.
- W2271037598 hasConcept C34388435 @default.
- W2271037598 hasConcept C34447519 @default.
- W2271037598 hasConcept C40506919 @default.
- W2271037598 hasConcept C41008148 @default.
- W2271037598 hasConcept C54355233 @default.
- W2271037598 hasConcept C75553542 @default.
- W2271037598 hasConcept C80444323 @default.
- W2271037598 hasConcept C86803240 @default.
- W2271037598 hasConceptScore W2271037598C111472728 @default.
- W2271037598 hasConceptScore W2271037598C118615104 @default.
- W2271037598 hasConceptScore W2271037598C119857082 @default.
- W2271037598 hasConceptScore W2271037598C134306372 @default.
- W2271037598 hasConceptScore W2271037598C138885662 @default.
- W2271037598 hasConceptScore W2271037598C154945302 @default.
- W2271037598 hasConceptScore W2271037598C162324750 @default.
- W2271037598 hasConceptScore W2271037598C2776214188 @default.
- W2271037598 hasConceptScore W2271037598C2778112365 @default.
- W2271037598 hasConceptScore W2271037598C2780990831 @default.
- W2271037598 hasConceptScore W2271037598C31170391 @default.
- W2271037598 hasConceptScore W2271037598C33923547 @default.
- W2271037598 hasConceptScore W2271037598C34388435 @default.
- W2271037598 hasConceptScore W2271037598C34447519 @default.
- W2271037598 hasConceptScore W2271037598C40506919 @default.
- W2271037598 hasConceptScore W2271037598C41008148 @default.
- W2271037598 hasConceptScore W2271037598C54355233 @default.
- W2271037598 hasConceptScore W2271037598C75553542 @default.
- W2271037598 hasConceptScore W2271037598C80444323 @default.
- W2271037598 hasConceptScore W2271037598C86803240 @default.
- W2271037598 hasLocation W22710375981 @default.
- W2271037598 hasOpenAccess W2271037598 @default.
- W2271037598 hasPrimaryLocation W22710375981 @default.
- W2271037598 hasRelatedWork W107094955 @default.
- W2271037598 hasRelatedWork W1502244627 @default.
- W2271037598 hasRelatedWork W1975630892 @default.
- W2271037598 hasRelatedWork W1989445634 @default.
- W2271037598 hasRelatedWork W2002286886 @default.
- W2271037598 hasRelatedWork W2040030484 @default.
- W2271037598 hasRelatedWork W2042755298 @default.
- W2271037598 hasRelatedWork W2087067957 @default.
- W2271037598 hasRelatedWork W2091143072 @default.
- W2271037598 hasRelatedWork W2110385897 @default.
- W2271037598 hasRelatedWork W2114991339 @default.
- W2271037598 hasRelatedWork W2123884022 @default.
- W2271037598 hasRelatedWork W2130608487 @default.
- W2271037598 hasRelatedWork W2221094098 @default.
- W2271037598 hasRelatedWork W2474443534 @default.
- W2271037598 hasRelatedWork W257599271 @default.
- W2271037598 hasRelatedWork W2785220241 @default.
- W2271037598 hasRelatedWork W2805996561 @default.
- W2271037598 hasRelatedWork W3021684942 @default.
- W2271037598 hasRelatedWork W3174029403 @default.
- W2271037598 hasVolume "136" @default.
- W2271037598 isParatext "false" @default.
- W2271037598 isRetracted "false" @default.
- W2271037598 magId "2271037598" @default.
- W2271037598 workType "article" @default.