Matches in SemOpenAlex for { <https://semopenalex.org/work/W1567331820> ?p ?o ?g. }
- W1567331820 endingPage "212" @default.
- W1567331820 startingPage "181" @default.
- W1567331820 abstract "We discuss Bayesian methods for model averaging and model selection among Bayesian-network models with hidden variables. In particular, we examine large-sample approximations for the marginal likelihood of naive-Bayes models in which the root node is hidden. Such models are useful for clustering or unsupervised learning. We consider a Laplace approximation and the less accurate but more computationally efficient approximation known as the Bayesian Information Criterion (BIC), which is equivalent to Rissanen's (1987) Minimum Description Length (MDL). Also, we consider approximations that ignore some off-diagonal elements of the observed information matrix and an approximation proposed by Cheeseman and Stutz (1995). We evaluate the accuracy of these approximations using a Monte-Carlo gold standard. In experiments with artificial and real examples, we find that (1) none of the approximations are accurate when used for model averaging, (2) all of the approximations, with the exception of BIC/MDL, are accurate for model selection, (3) among the accurate approximations, the Cheeseman–Stutz and Diagonal approximations are the most computationally efficient, (4) all of the approximations, with the exception of BIC/MDL, can be sensitive to the prior distribution over model parameters, and (5) the Cheeseman–Stutz approximation can be more accurate than the other approximations, including the Laplace approximation, in situations where the parameters in the maximum a posteriori configuration are near a boundary." @default.
- W1567331820 created "2016-06-24" @default.
- W1567331820 creator A5016386034 @default.
- W1567331820 creator A5038519100 @default.
- W1567331820 date "1997-01-01" @default.
- W1567331820 modified "2023-10-14" @default.
- W1567331820 cites W138052739 @default.
- W1567331820 cites W1488022545 @default.
- W1567331820 cites W1520448186 @default.
- W1567331820 cites W1524326598 @default.
- W1567331820 cites W1524704912 @default.
- W1567331820 cites W1537443165 @default.
- W1567331820 cites W1559849238 @default.
- W1567331820 cites W1669437150 @default.
- W1567331820 cites W1848663035 @default.
- W1567331820 cites W1887916728 @default.
- W1567331820 cites W19621276 @default.
- W1567331820 cites W1983772724 @default.
- W1567331820 cites W1985593448 @default.
- W1567331820 cites W1988520084 @default.
- W1567331820 cites W1998487261 @default.
- W1567331820 cites W2008906462 @default.
- W1567331820 cites W2015749074 @default.
- W1567331820 cites W2020999234 @default.
- W1567331820 cites W2027255954 @default.
- W1567331820 cites W2049633694 @default.
- W1567331820 cites W2060161465 @default.
- W1567331820 cites W2069469807 @default.
- W1567331820 cites W2074282020 @default.
- W1567331820 cites W2089763487 @default.
- W1567331820 cites W2100358124 @default.
- W1567331820 cites W2105716221 @default.
- W1567331820 cites W2111051539 @default.
- W1567331820 cites W2112514080 @default.
- W1567331820 cites W2126151607 @default.
- W1567331820 cites W2126163471 @default.
- W1567331820 cites W2130416410 @default.
- W1567331820 cites W2149337551 @default.
- W1567331820 cites W2168175751 @default.
- W1567331820 cites W2170112109 @default.
- W1567331820 cites W2330192890 @default.
- W1567331820 cites W2895369475 @default.
- W1567331820 cites W2911546748 @default.
- W1567331820 cites W2974222084 @default.
- W1567331820 cites W2982720039 @default.
- W1567331820 cites W3005512703 @default.
- W1567331820 cites W8978941 @default.
- W1567331820 doi "https://doi.org/10.1023/a:1007469629108" @default.
- W1567331820 hasPublicationYear "1997" @default.
- W1567331820 type Work @default.
- W1567331820 sameAs 1567331820 @default.
- W1567331820 citedByCount "282" @default.
- W1567331820 countsByYear W15673318202012 @default.
- W1567331820 countsByYear W15673318202013 @default.
- W1567331820 countsByYear W15673318202014 @default.
- W1567331820 countsByYear W15673318202015 @default.
- W1567331820 countsByYear W15673318202016 @default.
- W1567331820 countsByYear W15673318202017 @default.
- W1567331820 countsByYear W15673318202018 @default.
- W1567331820 countsByYear W15673318202019 @default.
- W1567331820 countsByYear W15673318202020 @default.
- W1567331820 countsByYear W15673318202021 @default.
- W1567331820 countsByYear W15673318202022 @default.
- W1567331820 countsByYear W15673318202023 @default.
- W1567331820 crossrefType "journal-article" @default.
- W1567331820 hasAuthorship W1567331820A5016386034 @default.
- W1567331820 hasAuthorship W1567331820A5038519100 @default.
- W1567331820 hasBestOaLocation W15673318201 @default.
- W1567331820 hasConcept C105795698 @default.
- W1567331820 hasConcept C107673813 @default.
- W1567331820 hasConcept C11413529 @default.
- W1567331820 hasConcept C130367717 @default.
- W1567331820 hasConcept C168136583 @default.
- W1567331820 hasConcept C22243797 @default.
- W1567331820 hasConcept C2524010 @default.
- W1567331820 hasConcept C28826006 @default.
- W1567331820 hasConcept C33923547 @default.
- W1567331820 hasConcept C49781872 @default.
- W1567331820 hasConcept C87465248 @default.
- W1567331820 hasConcept C93959086 @default.
- W1567331820 hasConcept C9810830 @default.
- W1567331820 hasConceptScore W1567331820C105795698 @default.
- W1567331820 hasConceptScore W1567331820C107673813 @default.
- W1567331820 hasConceptScore W1567331820C11413529 @default.
- W1567331820 hasConceptScore W1567331820C130367717 @default.
- W1567331820 hasConceptScore W1567331820C168136583 @default.
- W1567331820 hasConceptScore W1567331820C22243797 @default.
- W1567331820 hasConceptScore W1567331820C2524010 @default.
- W1567331820 hasConceptScore W1567331820C28826006 @default.
- W1567331820 hasConceptScore W1567331820C33923547 @default.
- W1567331820 hasConceptScore W1567331820C49781872 @default.
- W1567331820 hasConceptScore W1567331820C87465248 @default.
- W1567331820 hasConceptScore W1567331820C93959086 @default.
- W1567331820 hasConceptScore W1567331820C9810830 @default.
- W1567331820 hasIssue "2/3" @default.
- W1567331820 hasLocation W15673318201 @default.
- W1567331820 hasOpenAccess W1567331820 @default.
- W1567331820 hasPrimaryLocation W15673318201 @default.