Matches in SemOpenAlex for { <https://semopenalex.org/work/W2111659298> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2111659298 endingPage "459" @default.
- W2111659298 startingPage "452" @default.
- W2111659298 abstract "A new hybrid method is presented for designing feedforward, backpropagation neural models with small training data sets. The method minimizes the generalization error, a fundamental quantity that characterizes the effectiveness of the regression models. It combines into one framework a bootstrap technique that estimates network generalization performance and a collection of stochastic and deterministic optimization techniques that adjust neural network interconnection geometry. The approach is derived as a form of multi-objective optimization strategy. This allows for more direct treatment of contradictory design criteria than traditionally employed single-objectivetechniques.Astochasticoptimization methodsuch asageneticalgorithmisusedto selectactivation functions for hidden-layer nodes, whereas fast deterministic techniques, optimal brain surgeon and singular value decomposition, are used to perform connection and node pruning. The method is demonstrated by optimizing neural networks that model the high-lift aerodynamics of a multi-element airfoil. The neural model is constructed using a small computational data set consisting of 227 data points. In the numerical experiments presented, the solutions produced by this hybrid approach exhibit an improvement in the generalization ability on the average of e ve to six times when compared to the pruned models with only one type of activation function. When traditional fully connected networks with hyperbolic tangent activation functions are considered, the improvement in the generalization performance of the new models is even greater. The neural models exhibit superior generalization qualities that are virtually impossible to e nd by manual trial-and-error approaches." @default.
- W2111659298 created "2016-06-24" @default.
- W2111659298 creator A5002626557 @default.
- W2111659298 creator A5007247417 @default.
- W2111659298 creator A5023808822 @default.
- W2111659298 creator A5040846427 @default.
- W2111659298 date "2002-05-01" @default.
- W2111659298 modified "2023-09-27" @default.
- W2111659298 title "Designing Compact Feedforward Neural Models with Small Training Data Sets" @default.
- W2111659298 cites W1570129168 @default.
- W2111659298 cites W1965201499 @default.
- W2111659298 cites W2006544565 @default.
- W2111659298 cites W2021620982 @default.
- W2111659298 cites W2030302553 @default.
- W2111659298 cites W2072693551 @default.
- W2111659298 cites W2108384452 @default.
- W2111659298 cites W2113012682 @default.
- W2111659298 cites W2138665366 @default.
- W2111659298 cites W2171795060 @default.
- W2111659298 cites W2319329301 @default.
- W2111659298 cites W3106889297 @default.
- W2111659298 cites W4212883601 @default.
- W2111659298 cites W4214948567 @default.
- W2111659298 doi "https://doi.org/10.2514/2.2950" @default.
- W2111659298 hasPublicationYear "2002" @default.
- W2111659298 type Work @default.
- W2111659298 sameAs 2111659298 @default.
- W2111659298 citedByCount "7" @default.
- W2111659298 countsByYear W21116592982018 @default.
- W2111659298 countsByYear W21116592982023 @default.
- W2111659298 crossrefType "journal-article" @default.
- W2111659298 hasAuthorship W2111659298A5002626557 @default.
- W2111659298 hasAuthorship W2111659298A5007247417 @default.
- W2111659298 hasAuthorship W2111659298A5023808822 @default.
- W2111659298 hasAuthorship W2111659298A5040846427 @default.
- W2111659298 hasConcept C121332964 @default.
- W2111659298 hasConcept C127413603 @default.
- W2111659298 hasConcept C133731056 @default.
- W2111659298 hasConcept C153294291 @default.
- W2111659298 hasConcept C154945302 @default.
- W2111659298 hasConcept C2775924081 @default.
- W2111659298 hasConcept C2777211547 @default.
- W2111659298 hasConcept C38858127 @default.
- W2111659298 hasConcept C41008148 @default.
- W2111659298 hasConcept C47446073 @default.
- W2111659298 hasConcept C47702885 @default.
- W2111659298 hasConcept C50644808 @default.
- W2111659298 hasConceptScore W2111659298C121332964 @default.
- W2111659298 hasConceptScore W2111659298C127413603 @default.
- W2111659298 hasConceptScore W2111659298C133731056 @default.
- W2111659298 hasConceptScore W2111659298C153294291 @default.
- W2111659298 hasConceptScore W2111659298C154945302 @default.
- W2111659298 hasConceptScore W2111659298C2775924081 @default.
- W2111659298 hasConceptScore W2111659298C2777211547 @default.
- W2111659298 hasConceptScore W2111659298C38858127 @default.
- W2111659298 hasConceptScore W2111659298C41008148 @default.
- W2111659298 hasConceptScore W2111659298C47446073 @default.
- W2111659298 hasConceptScore W2111659298C47702885 @default.
- W2111659298 hasConceptScore W2111659298C50644808 @default.
- W2111659298 hasIssue "3" @default.
- W2111659298 hasLocation W21116592981 @default.
- W2111659298 hasOpenAccess W2111659298 @default.
- W2111659298 hasPrimaryLocation W21116592981 @default.
- W2111659298 hasRelatedWork W1604847762 @default.
- W2111659298 hasRelatedWork W1875742840 @default.
- W2111659298 hasRelatedWork W1905705329 @default.
- W2111659298 hasRelatedWork W2014323024 @default.
- W2111659298 hasRelatedWork W2086999410 @default.
- W2111659298 hasRelatedWork W2258992572 @default.
- W2111659298 hasRelatedWork W2359410228 @default.
- W2111659298 hasRelatedWork W2381165384 @default.
- W2111659298 hasRelatedWork W3177279640 @default.
- W2111659298 hasRelatedWork W4386132124 @default.
- W2111659298 hasVolume "39" @default.
- W2111659298 isParatext "false" @default.
- W2111659298 isRetracted "false" @default.
- W2111659298 magId "2111659298" @default.
- W2111659298 workType "article" @default.