Matches in SemOpenAlex for { <https://semopenalex.org/work/W1517128959> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W1517128959 abstract "Neural network learning rules can be viewed as statistical estimators. They should be studied in Bayesian framework even if they are not Bayesian estimators. Generalisation should be measured by the divergence between the true distribution and the estimated distribution. Information divergences are invariant measurements of the divergence between two distributions. The posterior average information divergence is used to measure the generalisation ability of a network. The optimal estimators for multinomial distributions with Dirichlet priors are studied in detail. This confirms that the definition is compatible with intuition. The results also show that many commonly used methods can be put under this unified framework, by assume special priors and special divergences." @default.
- W1517128959 created "2016-06-24" @default.
- W1517128959 creator A5060746228 @default.
- W1517128959 creator A5076801334 @default.
- W1517128959 date "1995-08-31" @default.
- W1517128959 modified "2023-09-27" @default.
- W1517128959 title "Bayesian invariant measurements of generalisation for discrete distributions" @default.
- W1517128959 hasPublicationYear "1995" @default.
- W1517128959 type Work @default.
- W1517128959 sameAs 1517128959 @default.
- W1517128959 citedByCount "2" @default.
- W1517128959 crossrefType "journal-article" @default.
- W1517128959 hasAuthorship W1517128959A5060746228 @default.
- W1517128959 hasAuthorship W1517128959A5076801334 @default.
- W1517128959 hasConcept C105795698 @default.
- W1517128959 hasConcept C107673813 @default.
- W1517128959 hasConcept C134306372 @default.
- W1517128959 hasConcept C138885662 @default.
- W1517128959 hasConcept C149441793 @default.
- W1517128959 hasConcept C154945302 @default.
- W1517128959 hasConcept C160234255 @default.
- W1517128959 hasConcept C169214877 @default.
- W1517128959 hasConcept C177769412 @default.
- W1517128959 hasConcept C182310444 @default.
- W1517128959 hasConcept C185429906 @default.
- W1517128959 hasConcept C190470478 @default.
- W1517128959 hasConcept C191413810 @default.
- W1517128959 hasConcept C192065140 @default.
- W1517128959 hasConcept C207390915 @default.
- W1517128959 hasConcept C28826006 @default.
- W1517128959 hasConcept C33923547 @default.
- W1517128959 hasConcept C37914503 @default.
- W1517128959 hasConcept C41008148 @default.
- W1517128959 hasConcept C41895202 @default.
- W1517128959 hasConcept C67926830 @default.
- W1517128959 hasConceptScore W1517128959C105795698 @default.
- W1517128959 hasConceptScore W1517128959C107673813 @default.
- W1517128959 hasConceptScore W1517128959C134306372 @default.
- W1517128959 hasConceptScore W1517128959C138885662 @default.
- W1517128959 hasConceptScore W1517128959C149441793 @default.
- W1517128959 hasConceptScore W1517128959C154945302 @default.
- W1517128959 hasConceptScore W1517128959C160234255 @default.
- W1517128959 hasConceptScore W1517128959C169214877 @default.
- W1517128959 hasConceptScore W1517128959C177769412 @default.
- W1517128959 hasConceptScore W1517128959C182310444 @default.
- W1517128959 hasConceptScore W1517128959C185429906 @default.
- W1517128959 hasConceptScore W1517128959C190470478 @default.
- W1517128959 hasConceptScore W1517128959C191413810 @default.
- W1517128959 hasConceptScore W1517128959C192065140 @default.
- W1517128959 hasConceptScore W1517128959C207390915 @default.
- W1517128959 hasConceptScore W1517128959C28826006 @default.
- W1517128959 hasConceptScore W1517128959C33923547 @default.
- W1517128959 hasConceptScore W1517128959C37914503 @default.
- W1517128959 hasConceptScore W1517128959C41008148 @default.
- W1517128959 hasConceptScore W1517128959C41895202 @default.
- W1517128959 hasConceptScore W1517128959C67926830 @default.
- W1517128959 hasLocation W15171289591 @default.
- W1517128959 hasOpenAccess W1517128959 @default.
- W1517128959 hasPrimaryLocation W15171289591 @default.
- W1517128959 hasRelatedWork W1602005819 @default.
- W1517128959 hasRelatedWork W1640105997 @default.
- W1517128959 hasRelatedWork W1776377774 @default.
- W1517128959 hasRelatedWork W1966457260 @default.
- W1517128959 hasRelatedWork W1974588608 @default.
- W1517128959 hasRelatedWork W1996814159 @default.
- W1517128959 hasRelatedWork W2056219143 @default.
- W1517128959 hasRelatedWork W2122477496 @default.
- W1517128959 hasRelatedWork W2141002476 @default.
- W1517128959 hasRelatedWork W2186258040 @default.
- W1517128959 hasRelatedWork W2203963652 @default.
- W1517128959 hasRelatedWork W2472610123 @default.
- W1517128959 hasRelatedWork W2517948014 @default.
- W1517128959 hasRelatedWork W2736278871 @default.
- W1517128959 hasRelatedWork W2804045927 @default.
- W1517128959 hasRelatedWork W2949454430 @default.
- W1517128959 hasRelatedWork W2965988157 @default.
- W1517128959 hasRelatedWork W3007638742 @default.
- W1517128959 hasRelatedWork W3023287005 @default.
- W1517128959 hasRelatedWork W3033672304 @default.
- W1517128959 isParatext "false" @default.
- W1517128959 isRetracted "false" @default.
- W1517128959 magId "1517128959" @default.
- W1517128959 workType "article" @default.