Matches in SemOpenAlex for { <https://semopenalex.org/work/W2153185970> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2153185970 endingPage "108" @default.
- W2153185970 startingPage "85" @default.
- W2153185970 abstract "A team of learning machines is a multiset of learning machines. A team is said to be successful just in case each member of some nonempty subset of the team is successful. The ratio of the number of machines required to be successful to the size of the team is referred to as the success ratio of the team. The present paper investigates for which success ratios can a team be replaced by a single machine without any loss in learning power. The answer depends on the concepts being learned and the criteria of success employed. For a given criterion of success, the minimum cut-off ratio where a team can be replaced by a single machine is referred to as the aggregation ratio of the criterion. The main results in the present paper concern aggregation ratios for vacillatory identification of languages from texts. According to this criterion of success, a learning machine is successful just in case it eventually vacillates between a finite set of grammars instead of converging to a single grammar. For a positive integer n, a machine is said to TxtFexn-identify a language L just in case the machine converges to up to n grammars for L on any text for L. For such identification criteria, the aggregation ratio is derived for the case n = 2. It is shown that the collection of languages that can be TxtFex2-identified by teams with success ratio greater than 56 are the same as those collections of languages that can be TxtFex2-identified by a single machine. It is also established that 56 is indeed the cut-off point by showing that there are collections of languages that can be TxtFex2-identified by a team employing six machines, at least five of which are required to be successful, but cannot be TxtFex2-identified by any single machine. Additionally, aggregation ratios are also derived for finite identification of languages from positive data and for numerous criteria involving language learning from both positive and negative data." @default.
- W2153185970 created "2016-06-24" @default.
- W2153185970 creator A5008299613 @default.
- W2153185970 creator A5033626728 @default.
- W2153185970 date "1995-01-01" @default.
- W2153185970 modified "2023-09-27" @default.
- W2153185970 title "On aggregating teams of learning machines" @default.
- W2153185970 cites W150311997 @default.
- W2153185970 cites W1579083493 @default.
- W2153185970 cites W1632759684 @default.
- W2153185970 cites W1785196451 @default.
- W2153185970 cites W1963780006 @default.
- W2153185970 cites W1967434608 @default.
- W2153185970 cites W1969005071 @default.
- W2153185970 cites W1969335312 @default.
- W2153185970 cites W1970567684 @default.
- W2153185970 cites W2002089154 @default.
- W2153185970 cites W2006065467 @default.
- W2153185970 cites W2017636732 @default.
- W2153185970 cites W2018722248 @default.
- W2153185970 cites W2025962687 @default.
- W2153185970 cites W2041249678 @default.
- W2153185970 cites W2041709321 @default.
- W2153185970 cites W2052493080 @default.
- W2153185970 cites W2067619284 @default.
- W2153185970 cites W2089442854 @default.
- W2153185970 cites W2121337085 @default.
- W2153185970 cites W2150510043 @default.
- W2153185970 cites W2530006810 @default.
- W2153185970 cites W54294191 @default.
- W2153185970 doi "https://doi.org/10.1016/0304-3975(94)00162-c" @default.
- W2153185970 hasPublicationYear "1995" @default.
- W2153185970 type Work @default.
- W2153185970 sameAs 2153185970 @default.
- W2153185970 citedByCount "9" @default.
- W2153185970 countsByYear W21531859702015 @default.
- W2153185970 crossrefType "journal-article" @default.
- W2153185970 hasAuthorship W2153185970A5008299613 @default.
- W2153185970 hasAuthorship W2153185970A5033626728 @default.
- W2153185970 hasConcept C116834253 @default.
- W2153185970 hasConcept C118615104 @default.
- W2153185970 hasConcept C119857082 @default.
- W2153185970 hasConcept C138885662 @default.
- W2153185970 hasConcept C154945302 @default.
- W2153185970 hasConcept C177264268 @default.
- W2153185970 hasConcept C199360897 @default.
- W2153185970 hasConcept C204321447 @default.
- W2153185970 hasConcept C26022165 @default.
- W2153185970 hasConcept C2779623528 @default.
- W2153185970 hasConcept C33923547 @default.
- W2153185970 hasConcept C41008148 @default.
- W2153185970 hasConcept C41895202 @default.
- W2153185970 hasConcept C53893814 @default.
- W2153185970 hasConcept C59822182 @default.
- W2153185970 hasConcept C86803240 @default.
- W2153185970 hasConcept C97137487 @default.
- W2153185970 hasConceptScore W2153185970C116834253 @default.
- W2153185970 hasConceptScore W2153185970C118615104 @default.
- W2153185970 hasConceptScore W2153185970C119857082 @default.
- W2153185970 hasConceptScore W2153185970C138885662 @default.
- W2153185970 hasConceptScore W2153185970C154945302 @default.
- W2153185970 hasConceptScore W2153185970C177264268 @default.
- W2153185970 hasConceptScore W2153185970C199360897 @default.
- W2153185970 hasConceptScore W2153185970C204321447 @default.
- W2153185970 hasConceptScore W2153185970C26022165 @default.
- W2153185970 hasConceptScore W2153185970C2779623528 @default.
- W2153185970 hasConceptScore W2153185970C33923547 @default.
- W2153185970 hasConceptScore W2153185970C41008148 @default.
- W2153185970 hasConceptScore W2153185970C41895202 @default.
- W2153185970 hasConceptScore W2153185970C53893814 @default.
- W2153185970 hasConceptScore W2153185970C59822182 @default.
- W2153185970 hasConceptScore W2153185970C86803240 @default.
- W2153185970 hasConceptScore W2153185970C97137487 @default.
- W2153185970 hasIssue "1" @default.
- W2153185970 hasLocation W21531859701 @default.
- W2153185970 hasOpenAccess W2153185970 @default.
- W2153185970 hasPrimaryLocation W21531859701 @default.
- W2153185970 hasRelatedWork W1512634710 @default.
- W2153185970 hasRelatedWork W1569841287 @default.
- W2153185970 hasRelatedWork W1585034923 @default.
- W2153185970 hasRelatedWork W2022050541 @default.
- W2153185970 hasRelatedWork W2096353963 @default.
- W2153185970 hasRelatedWork W2167662847 @default.
- W2153185970 hasRelatedWork W2340909594 @default.
- W2153185970 hasRelatedWork W2789919619 @default.
- W2153185970 hasRelatedWork W3107474891 @default.
- W2153185970 hasRelatedWork W2594281132 @default.
- W2153185970 hasVolume "137" @default.
- W2153185970 isParatext "false" @default.
- W2153185970 isRetracted "false" @default.
- W2153185970 magId "2153185970" @default.
- W2153185970 workType "article" @default.