Matches in SemOpenAlex for { <https://semopenalex.org/work/W2940859364> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2940859364 endingPage "012074" @default.
- W2940859364 startingPage "012074" @default.
- W2940859364 abstract "The paper suggests an extended version of principle of empirical risk minimization and principle of smoothly winsorized averages minimization for robust neural networks learning. It's based on using of M-averaging and WM-averaging functions instead of the arithmetic mean for empirical risk estimation. These approaches generalize robust algorithms based on using median and quantiles for estimation of mean losses. An iteratively reweighted schema for minimization of differentiable robust estimations of the averages of loss functions is proposed. This schema allows to use weighted version of traditional back-propagation algorithms for neural networks learning in presence of outliers." @default.
- W2940859364 created "2019-05-03" @default.
- W2940859364 creator A5023366934 @default.
- W2940859364 creator A5031940141 @default.
- W2940859364 creator A5085267629 @default.
- W2940859364 date "2019-04-01" @default.
- W2940859364 modified "2023-09-26" @default.
- W2940859364 title "Robust training of neural network via minimizing robust estimates of the average of loss functions" @default.
- W2940859364 cites W1534675906 @default.
- W2940859364 cites W1964524778 @default.
- W2940859364 cites W2020647418 @default.
- W2940859364 cites W2050551672 @default.
- W2940859364 cites W2071413401 @default.
- W2940859364 cites W2130441379 @default.
- W2940859364 cites W2137983211 @default.
- W2940859364 cites W2141547648 @default.
- W2940859364 cites W2152701363 @default.
- W2940859364 cites W2489822048 @default.
- W2940859364 cites W2766217071 @default.
- W2940859364 cites W4255230573 @default.
- W2940859364 doi "https://doi.org/10.1088/1742-6596/1203/1/012074" @default.
- W2940859364 hasPublicationYear "2019" @default.
- W2940859364 type Work @default.
- W2940859364 sameAs 2940859364 @default.
- W2940859364 citedByCount "1" @default.
- W2940859364 countsByYear W29408593642020 @default.
- W2940859364 crossrefType "journal-article" @default.
- W2940859364 hasAuthorship W2940859364A5023366934 @default.
- W2940859364 hasAuthorship W2940859364A5031940141 @default.
- W2940859364 hasAuthorship W2940859364A5085267629 @default.
- W2940859364 hasBestOaLocation W29408593641 @default.
- W2940859364 hasConcept C104317684 @default.
- W2940859364 hasConcept C105795698 @default.
- W2940859364 hasConcept C107321475 @default.
- W2940859364 hasConcept C11413529 @default.
- W2940859364 hasConcept C118671147 @default.
- W2940859364 hasConcept C126255220 @default.
- W2940859364 hasConcept C134306372 @default.
- W2940859364 hasConcept C147764199 @default.
- W2940859364 hasConcept C154945302 @default.
- W2940859364 hasConcept C185429906 @default.
- W2940859364 hasConcept C185592680 @default.
- W2940859364 hasConcept C202615002 @default.
- W2940859364 hasConcept C33923547 @default.
- W2940859364 hasConcept C41008148 @default.
- W2940859364 hasConcept C50644808 @default.
- W2940859364 hasConcept C55493867 @default.
- W2940859364 hasConcept C63479239 @default.
- W2940859364 hasConcept C79337645 @default.
- W2940859364 hasConceptScore W2940859364C104317684 @default.
- W2940859364 hasConceptScore W2940859364C105795698 @default.
- W2940859364 hasConceptScore W2940859364C107321475 @default.
- W2940859364 hasConceptScore W2940859364C11413529 @default.
- W2940859364 hasConceptScore W2940859364C118671147 @default.
- W2940859364 hasConceptScore W2940859364C126255220 @default.
- W2940859364 hasConceptScore W2940859364C134306372 @default.
- W2940859364 hasConceptScore W2940859364C147764199 @default.
- W2940859364 hasConceptScore W2940859364C154945302 @default.
- W2940859364 hasConceptScore W2940859364C185429906 @default.
- W2940859364 hasConceptScore W2940859364C185592680 @default.
- W2940859364 hasConceptScore W2940859364C202615002 @default.
- W2940859364 hasConceptScore W2940859364C33923547 @default.
- W2940859364 hasConceptScore W2940859364C41008148 @default.
- W2940859364 hasConceptScore W2940859364C50644808 @default.
- W2940859364 hasConceptScore W2940859364C55493867 @default.
- W2940859364 hasConceptScore W2940859364C63479239 @default.
- W2940859364 hasConceptScore W2940859364C79337645 @default.
- W2940859364 hasLocation W29408593641 @default.
- W2940859364 hasOpenAccess W2940859364 @default.
- W2940859364 hasPrimaryLocation W29408593641 @default.
- W2940859364 hasRelatedWork W1980763893 @default.
- W2940859364 hasRelatedWork W2017293492 @default.
- W2940859364 hasRelatedWork W2040956903 @default.
- W2940859364 hasRelatedWork W2055991171 @default.
- W2940859364 hasRelatedWork W2292842243 @default.
- W2940859364 hasRelatedWork W2807702091 @default.
- W2940859364 hasRelatedWork W2948699498 @default.
- W2940859364 hasRelatedWork W4232379160 @default.
- W2940859364 hasRelatedWork W73199774 @default.
- W2940859364 hasRelatedWork W3015906298 @default.
- W2940859364 hasVolume "1203" @default.
- W2940859364 isParatext "false" @default.
- W2940859364 isRetracted "false" @default.
- W2940859364 magId "2940859364" @default.
- W2940859364 workType "article" @default.