FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2068347708> ?p ?o ?g. }

• W2068347708 endingPage "322" @default.
• W2068347708 startingPage "275" @default.
• W2068347708 abstract "In the setting of learning indexed families, probabilistic learning under monotonicity constraints is more powerful than deterministic learning under monotonicity constraints, even if the probability is close to 1 , provided the learning machines are restricted to proper or class preserving hypothesis spaces (cf. Meyer, Theoret. Comput. Sci. 185 (1997) 81–128). In this paper, we investigate the relation between probabilistic learning and oracle identification under monotonicity constraints. In particular, we deal with the question how much additional information provided by oracles is necessary for compensating the additional power of probabilistic learning machines. In Section 1 , we show that K is necessary and sufficient to compensate the additional power of probabilistic learning machines in the case of conservative (monotonic) probabilistic learning with p>1/2 (p>2/3) , and for strong-monotonic probabilistic learning with 1/2<p⩽2/3 . In the case of strong-monotonic learning with p>2/3 , however, every Peano-complete oracle is sufficient for compensating the power of probabilistic learning machines. In contrast, the oracle K is not sufficient for compensating the power of conservative and strong-monotonic probabilistic learning with probability p=1/2 , and monotonic probabilistic learning with p=2/3 . The main result in Section 2 is that for each oracle A⩽ T K , there exists an indexed family L A which is properly conservatively identifiable with p=1/2 , and which exactly reflects the Turing degree of A , i.e., L A is properly conservatively identifiable by an oracle machine M[B] iff A⩽ T B . Thus, for every oracle A below K , we can construct a learning problem characterizing A within proper conservative learning. However, not every indexed family which is conservatively identifiable with probability p=1/2 reflects the Turing degree of an oracle. Hence, the conservative probabilistic learning classes are higher structured than the Turing degrees below K . Finally, we prove that there exist learning problems which are conservatively (monotonically) identifiable with probability p=1/2 (p=2/3) , but conservatively (monotonically) identifiable only by oracle machines having access to TOT . For strong-monotonic learning, this result does not hold." @default.
• W2068347708 created "2016-06-24" @default.
• W2068347708 creator A5071637503 @default.
• W2068347708 date "2001-10-01" @default.
• W2068347708 modified "2023-10-16" @default.
• W2068347708 title "Aspects of complexity of probabilistic learning under monotonicity constraints" @default.
• W2068347708 cites W1204180744 @default.
• W2068347708 cites W128891287 @default.
• W2068347708 cites W1491038035 @default.
• W2068347708 cites W1495082528 @default.
• W2068347708 cites W1514625626 @default.
• W2068347708 cites W1558153169 @default.
• W2068347708 cites W1564062284 @default.
• W2068347708 cites W1566918015 @default.
• W2068347708 cites W1575192246 @default.
• W2068347708 cites W1592190919 @default.
• W2068347708 cites W1602955616 @default.
• W2068347708 cites W1632759684 @default.
• W2068347708 cites W1794244844 @default.
• W2068347708 cites W1969005071 @default.
• W2068347708 cites W1970567684 @default.
• W2068347708 cites W1980102195 @default.
• W2068347708 cites W1984676934 @default.
• W2068347708 cites W1989445634 @default.
• W2068347708 cites W1995000122 @default.
• W2068347708 cites W1997380360 @default.
• W2068347708 cites W1998958764 @default.
• W2068347708 cites W1999832284 @default.
• W2068347708 cites W2002089154 @default.
• W2068347708 cites W2010503964 @default.
• W2068347708 cites W2019001600 @default.
• W2068347708 cites W2019363670 @default.
• W2068347708 cites W2025980794 @default.
• W2068347708 cites W2056414301 @default.
• W2068347708 cites W2058721256 @default.
• W2068347708 cites W2063688469 @default.
• W2068347708 cites W2064496697 @default.
• W2068347708 cites W2064984186 @default.
• W2068347708 cites W2067748079 @default.
• W2068347708 cites W2070494326 @default.
• W2068347708 cites W2071654679 @default.
• W2068347708 cites W2083944424 @default.
• W2068347708 cites W2089442854 @default.
• W2068347708 cites W2173983769 @default.
• W2068347708 cites W2174562085 @default.
• W2068347708 cites W26772505 @default.
• W2068347708 cites W35112329 @default.
• W2068347708 cites W623765668 @default.
• W2068347708 cites W70537844 @default.
• W2068347708 doi "https://doi.org/10.1016/s0304-3975(00)00273-5" @default.
• W2068347708 hasPublicationYear "2001" @default.
• W2068347708 type Work @default.
• W2068347708 sameAs 2068347708 @default.
• W2068347708 citedByCount "1" @default.
• W2068347708 countsByYear W20683477082014 @default.
• W2068347708 crossrefType "journal-article" @default.
• W2068347708 hasAuthorship W2068347708A5071637503 @default.
• W2068347708 hasBestOaLocation W20683477081 @default.
• W2068347708 hasConcept C118615104 @default.
• W2068347708 hasConcept C134306372 @default.
• W2068347708 hasConcept C144237770 @default.
• W2068347708 hasConcept C154945302 @default.
• W2068347708 hasConcept C33923547 @default.
• W2068347708 hasConcept C41008148 @default.
• W2068347708 hasConcept C49937458 @default.
• W2068347708 hasConcept C72169020 @default.
• W2068347708 hasConcept C80444323 @default.
• W2068347708 hasConceptScore W2068347708C118615104 @default.
• W2068347708 hasConceptScore W2068347708C134306372 @default.
• W2068347708 hasConceptScore W2068347708C144237770 @default.
• W2068347708 hasConceptScore W2068347708C154945302 @default.
• W2068347708 hasConceptScore W2068347708C33923547 @default.
• W2068347708 hasConceptScore W2068347708C41008148 @default.
• W2068347708 hasConceptScore W2068347708C49937458 @default.
• W2068347708 hasConceptScore W2068347708C72169020 @default.
• W2068347708 hasConceptScore W2068347708C80444323 @default.
• W2068347708 hasIssue "2" @default.
• W2068347708 hasLocation W20683477081 @default.
• W2068347708 hasOpenAccess W2068347708 @default.
• W2068347708 hasPrimaryLocation W20683477081 @default.
• W2068347708 hasRelatedWork W2009650958 @default.
• W2068347708 hasRelatedWork W2014538672 @default.
• W2068347708 hasRelatedWork W2029109849 @default.
• W2068347708 hasRelatedWork W2047600461 @default.
• W2068347708 hasRelatedWork W2080268478 @default.
• W2068347708 hasRelatedWork W2258540550 @default.
• W2068347708 hasRelatedWork W3029612563 @default.
• W2068347708 hasRelatedWork W3122236022 @default.
• W2068347708 hasRelatedWork W3124525543 @default.
• W2068347708 hasRelatedWork W3126127750 @default.
• W2068347708 hasVolume "268" @default.
• W2068347708 isParatext "false" @default.
• W2068347708 isRetracted "false" @default.
• W2068347708 magId "2068347708" @default.
• W2068347708 workType "article" @default.