Matches in SemOpenAlex for { <https://semopenalex.org/work/W2156660219> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2156660219 endingPage "142" @default.
- W2156660219 startingPage "109" @default.
- W2156660219 abstract "It is easy to design on-line learning algorithms for learning k out of n variable monotone disjunctions by simply keeping one weight per disjunction. Such algorithms use roughly O(nk) weights which can be prohibitively expensive. Surprisingly, algorithms like Winnow require only n weights (one per variable or attribute) and the mistake bound of these algorithms is not too much worse than the mistake bound of the more costly algorithms. The purpose of this paper is to investigate how exponentially many weights can be collapsed into only O(n) weights. In particular, we consider probabilistic assumptions that enable the Bayes optimal algorithm's posterior over the disjunctions to be encoded with only O(n) weights. This results in a new O(n) algorithm for learning disjunctions which is related to the Bylander's BEG algorithm originally introduced for linear regression. Besides providing a Bayesian interpretation for this new algorithm, we are also able to obtain mistake bounds for the noise free case resembling those that have been derived for the Winnow algorithm. The same techniques used to derive this new algorithm also provide a Bayesian interpretation for a normalized version of Winnow." @default.
- W2156660219 created "2016-06-24" @default.
- W2156660219 creator A5014740431 @default.
- W2156660219 creator A5071906735 @default.
- W2156660219 creator A5079068357 @default.
- W2156660219 date "2002-07-01" @default.
- W2156660219 modified "2023-10-18" @default.
- W2156660219 title "Direct and indirect algorithms for on-line learning of disjunctions" @default.
- W2156660219 cites W1507029541 @default.
- W2156660219 cites W1562209977 @default.
- W2156660219 cites W1587647246 @default.
- W2156660219 cites W2038951246 @default.
- W2156660219 cites W2065861851 @default.
- W2156660219 cites W2093825590 @default.
- W2156660219 cites W2102800374 @default.
- W2156660219 cites W2129113961 @default.
- W2156660219 cites W2162953025 @default.
- W2156660219 cites W2163046677 @default.
- W2156660219 cites W3017143921 @default.
- W2156660219 doi "https://doi.org/10.1016/s0304-3975(01)00081-0" @default.
- W2156660219 hasPublicationYear "2002" @default.
- W2156660219 type Work @default.
- W2156660219 sameAs 2156660219 @default.
- W2156660219 citedByCount "8" @default.
- W2156660219 countsByYear W21566602192015 @default.
- W2156660219 countsByYear W21566602192016 @default.
- W2156660219 crossrefType "journal-article" @default.
- W2156660219 hasAuthorship W2156660219A5014740431 @default.
- W2156660219 hasAuthorship W2156660219A5071906735 @default.
- W2156660219 hasAuthorship W2156660219A5079068357 @default.
- W2156660219 hasConcept C107673813 @default.
- W2156660219 hasConcept C11413529 @default.
- W2156660219 hasConcept C134306372 @default.
- W2156660219 hasConcept C154945302 @default.
- W2156660219 hasConcept C17744445 @default.
- W2156660219 hasConcept C182365436 @default.
- W2156660219 hasConcept C199360897 @default.
- W2156660219 hasConcept C199539241 @default.
- W2156660219 hasConcept C24404364 @default.
- W2156660219 hasConcept C2524010 @default.
- W2156660219 hasConcept C2777179996 @default.
- W2156660219 hasConcept C2834757 @default.
- W2156660219 hasConcept C33923547 @default.
- W2156660219 hasConcept C41008148 @default.
- W2156660219 hasConcept C49937458 @default.
- W2156660219 hasConcept C527412718 @default.
- W2156660219 hasConceptScore W2156660219C107673813 @default.
- W2156660219 hasConceptScore W2156660219C11413529 @default.
- W2156660219 hasConceptScore W2156660219C134306372 @default.
- W2156660219 hasConceptScore W2156660219C154945302 @default.
- W2156660219 hasConceptScore W2156660219C17744445 @default.
- W2156660219 hasConceptScore W2156660219C182365436 @default.
- W2156660219 hasConceptScore W2156660219C199360897 @default.
- W2156660219 hasConceptScore W2156660219C199539241 @default.
- W2156660219 hasConceptScore W2156660219C24404364 @default.
- W2156660219 hasConceptScore W2156660219C2524010 @default.
- W2156660219 hasConceptScore W2156660219C2777179996 @default.
- W2156660219 hasConceptScore W2156660219C2834757 @default.
- W2156660219 hasConceptScore W2156660219C33923547 @default.
- W2156660219 hasConceptScore W2156660219C41008148 @default.
- W2156660219 hasConceptScore W2156660219C49937458 @default.
- W2156660219 hasConceptScore W2156660219C527412718 @default.
- W2156660219 hasIssue "1" @default.
- W2156660219 hasLocation W21566602191 @default.
- W2156660219 hasOpenAccess W2156660219 @default.
- W2156660219 hasPrimaryLocation W21566602191 @default.
- W2156660219 hasRelatedWork W1970358763 @default.
- W2156660219 hasRelatedWork W2078590855 @default.
- W2156660219 hasRelatedWork W2151268798 @default.
- W2156660219 hasRelatedWork W2212155158 @default.
- W2156660219 hasRelatedWork W2332263680 @default.
- W2156660219 hasRelatedWork W2548393475 @default.
- W2156660219 hasRelatedWork W2568527750 @default.
- W2156660219 hasRelatedWork W2969465628 @default.
- W2156660219 hasRelatedWork W4311518494 @default.
- W2156660219 hasRelatedWork W2132214879 @default.
- W2156660219 hasVolume "284" @default.
- W2156660219 isParatext "false" @default.
- W2156660219 isRetracted "false" @default.
- W2156660219 magId "2156660219" @default.
- W2156660219 workType "article" @default.