Matches in SemOpenAlex for { <https://semopenalex.org/work/W126232561> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W126232561 abstract "Training neural networks for predicting conditional probability densities can be accelerated considerably by adopting the random vector functional link net (RVFL) approach.In this way, a whole ensemble of models can be trained at the same computationalcosts as otherwise required for training only one conventional network. The inherentstochasticity of the RVFL method increases the diversity in this ensemble, which leadsto a signi cant reduction of the generalisation error. The application of this scheme toa synthetic multimodal stochastic time series and a real-world benchmark problem wasfound to achieve a performance better than or comparable to the best results otherwise obtained so far. Moreover, the simulations support a recent theoretical study andshow that when making predictions with network committees, it can be advantageousto employ underregularised models that overfit the training data" @default.
- W126232561 created "2016-06-24" @default.
- W126232561 creator A5006045418 @default.
- W126232561 creator A5080836461 @default.
- W126232561 date "1998-01-01" @default.
- W126232561 modified "2023-09-26" @default.
- W126232561 title "Modelling conditional probabilities with network committees: how overfitting can be useful" @default.
- W126232561 hasPublicationYear "1998" @default.
- W126232561 type Work @default.
- W126232561 sameAs 126232561 @default.
- W126232561 citedByCount "3" @default.
- W126232561 countsByYear W1262325612013 @default.
- W126232561 crossrefType "journal-article" @default.
- W126232561 hasAuthorship W126232561A5006045418 @default.
- W126232561 hasAuthorship W126232561A5080836461 @default.
- W126232561 hasConcept C11413529 @default.
- W126232561 hasConcept C119857082 @default.
- W126232561 hasConcept C13280743 @default.
- W126232561 hasConcept C150921843 @default.
- W126232561 hasConcept C154945302 @default.
- W126232561 hasConcept C185798385 @default.
- W126232561 hasConcept C205649164 @default.
- W126232561 hasConcept C22019652 @default.
- W126232561 hasConcept C41008148 @default.
- W126232561 hasConcept C50644808 @default.
- W126232561 hasConcept C5465570 @default.
- W126232561 hasConceptScore W126232561C11413529 @default.
- W126232561 hasConceptScore W126232561C119857082 @default.
- W126232561 hasConceptScore W126232561C13280743 @default.
- W126232561 hasConceptScore W126232561C150921843 @default.
- W126232561 hasConceptScore W126232561C154945302 @default.
- W126232561 hasConceptScore W126232561C185798385 @default.
- W126232561 hasConceptScore W126232561C205649164 @default.
- W126232561 hasConceptScore W126232561C22019652 @default.
- W126232561 hasConceptScore W126232561C41008148 @default.
- W126232561 hasConceptScore W126232561C50644808 @default.
- W126232561 hasConceptScore W126232561C5465570 @default.
- W126232561 hasLocation W1262325611 @default.
- W126232561 hasOpenAccess W126232561 @default.
- W126232561 hasPrimaryLocation W1262325611 @default.
- W126232561 hasRelatedWork W1504988876 @default.
- W126232561 hasRelatedWork W2085867967 @default.
- W126232561 hasRelatedWork W2522733224 @default.
- W126232561 hasRelatedWork W2892124927 @default.
- W126232561 hasRelatedWork W2912626019 @default.
- W126232561 hasRelatedWork W2951728450 @default.
- W126232561 hasRelatedWork W2979906247 @default.
- W126232561 hasRelatedWork W3010624034 @default.
- W126232561 hasRelatedWork W3015036596 @default.
- W126232561 hasRelatedWork W3021166038 @default.
- W126232561 hasRelatedWork W3036124210 @default.
- W126232561 hasRelatedWork W3049255282 @default.
- W126232561 hasRelatedWork W3130238021 @default.
- W126232561 hasRelatedWork W3131195611 @default.
- W126232561 hasRelatedWork W3135338544 @default.
- W126232561 hasRelatedWork W3143318664 @default.
- W126232561 hasRelatedWork W3179598584 @default.
- W126232561 hasRelatedWork W3185990877 @default.
- W126232561 hasRelatedWork W3194779779 @default.
- W126232561 hasRelatedWork W3208281152 @default.
- W126232561 isParatext "false" @default.
- W126232561 isRetracted "false" @default.
- W126232561 magId "126232561" @default.
- W126232561 workType "article" @default.