Matches in SemOpenAlex for { <https://semopenalex.org/work/W2109439381> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2109439381 endingPage "546" @default.
- W2109439381 startingPage "539" @default.
- W2109439381 abstract "The Bayesian approximation has recently been employed to determine the noise and weight-penalty terms used in back-propagation. This paper shows that for neural nets it is far easier to use the exact result than it is to use the evidence approximation. Moreover, unlike the evidence approximation, the exact result neither has to be re-calculated for every new data set, nor requires the running of computer code (the exact result is closed form). In addition, it turns out that the evidence procedure's MAP estimate for neural nets is, in toto, approximation error. Another advantage of the exact analysis is that it does not lead one to incorrect intuition, like the claim that using evidence one can evaluate different priors in light of the data. This paper also discusses sufficiency conditions for the evidence approximation to hold, why it can sometimes give reasonable results, etc." @default.
- W2109439381 created "2016-06-24" @default.
- W2109439381 creator A5073514351 @default.
- W2109439381 date "1992-11-30" @default.
- W2109439381 modified "2023-09-24" @default.
- W2109439381 title "On the Use of Evidence in Neural Networks" @default.
- W2109439381 cites W1597345203 @default.
- W2109439381 cites W2109554147 @default.
- W2109439381 cites W2111051539 @default.
- W2109439381 cites W2727300753 @default.
- W2109439381 cites W2911546748 @default.
- W2109439381 hasPublicationYear "1992" @default.
- W2109439381 type Work @default.
- W2109439381 sameAs 2109439381 @default.
- W2109439381 citedByCount "0" @default.
- W2109439381 crossrefType "proceedings-article" @default.
- W2109439381 hasAuthorship W2109439381A5073514351 @default.
- W2109439381 hasConcept C107673813 @default.
- W2109439381 hasConcept C111472728 @default.
- W2109439381 hasConcept C11413529 @default.
- W2109439381 hasConcept C115961682 @default.
- W2109439381 hasConcept C122383733 @default.
- W2109439381 hasConcept C126255220 @default.
- W2109439381 hasConcept C132010649 @default.
- W2109439381 hasConcept C138885662 @default.
- W2109439381 hasConcept C148764684 @default.
- W2109439381 hasConcept C154945302 @default.
- W2109439381 hasConcept C177264268 @default.
- W2109439381 hasConcept C199360897 @default.
- W2109439381 hasConcept C33923547 @default.
- W2109439381 hasConcept C41008148 @default.
- W2109439381 hasConcept C50644808 @default.
- W2109439381 hasConcept C99498987 @default.
- W2109439381 hasConceptScore W2109439381C107673813 @default.
- W2109439381 hasConceptScore W2109439381C111472728 @default.
- W2109439381 hasConceptScore W2109439381C11413529 @default.
- W2109439381 hasConceptScore W2109439381C115961682 @default.
- W2109439381 hasConceptScore W2109439381C122383733 @default.
- W2109439381 hasConceptScore W2109439381C126255220 @default.
- W2109439381 hasConceptScore W2109439381C132010649 @default.
- W2109439381 hasConceptScore W2109439381C138885662 @default.
- W2109439381 hasConceptScore W2109439381C148764684 @default.
- W2109439381 hasConceptScore W2109439381C154945302 @default.
- W2109439381 hasConceptScore W2109439381C177264268 @default.
- W2109439381 hasConceptScore W2109439381C199360897 @default.
- W2109439381 hasConceptScore W2109439381C33923547 @default.
- W2109439381 hasConceptScore W2109439381C41008148 @default.
- W2109439381 hasConceptScore W2109439381C50644808 @default.
- W2109439381 hasConceptScore W2109439381C99498987 @default.
- W2109439381 hasLocation W21094393811 @default.
- W2109439381 hasOpenAccess W2109439381 @default.
- W2109439381 hasPrimaryLocation W21094393811 @default.
- W2109439381 hasRelatedWork W1185084623 @default.
- W2109439381 hasRelatedWork W1748004346 @default.
- W2109439381 hasRelatedWork W1985791397 @default.
- W2109439381 hasRelatedWork W2013327003 @default.
- W2109439381 hasRelatedWork W2077390566 @default.
- W2109439381 hasRelatedWork W2096691391 @default.
- W2109439381 hasRelatedWork W2101968469 @default.
- W2109439381 hasRelatedWork W2105644481 @default.
- W2109439381 hasRelatedWork W2115685415 @default.
- W2109439381 hasRelatedWork W2123147097 @default.
- W2109439381 hasRelatedWork W2144724317 @default.
- W2109439381 hasRelatedWork W2151257151 @default.
- W2109439381 hasRelatedWork W2612976922 @default.
- W2109439381 hasRelatedWork W2950906236 @default.
- W2109439381 hasRelatedWork W2972277540 @default.
- W2109439381 hasRelatedWork W3030196398 @default.
- W2109439381 hasRelatedWork W3037840371 @default.
- W2109439381 hasRelatedWork W3083720136 @default.
- W2109439381 hasRelatedWork W3122150125 @default.
- W2109439381 hasRelatedWork W3158012060 @default.
- W2109439381 hasVolume "5" @default.
- W2109439381 isParatext "false" @default.
- W2109439381 isRetracted "false" @default.
- W2109439381 magId "2109439381" @default.
- W2109439381 workType "article" @default.