FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2790097789> ?p ?o ?g. }

• W2790097789 endingPage "106" @default.
• W2790097789 startingPage "98" @default.
• W2790097789 abstract "In the construction of an artificial neural network (ANN) a proper data splitting of the available samples plays a major role in the training process. This selection of subsets for training, testing and validation affects the generalization ability of the neural network. Also the number of samples has an impact in the time required for the design of the ANN and the training. This paper introduces an efficient and simple method for reducing the set of samples used for training a neural network. The method reduces the required time to calculate the network coefficients, while keeping the diversity and avoiding overtraining the ANN due the presence of similar samples. The proposed method is based on the calculation of the angle between two vectors, each one representing one input of the neural network. When the angle formed among samples is smaller than a defined threshold only one input is accepted for the training. The accepted inputs are scattered throughout the sample space. Tidal records are used to demonstrate the proposed method. The results of a cross-validation show that with few inputs the quality of the outputs is not accurate and depends on the selection of the first sample, but as the number of inputs increases the accuracy is improved and differences among the scenarios with a different starting sample have and important reduction. A comparison with the K-means clustering algorithm shows that for this application the proposed method with a smaller number of samples is producing a more accurate network." @default.
• W2790097789 created "2018-03-29" @default.
• W2790097789 creator A5027742375 @default.
• W2790097789 creator A5067966144 @default.
• W2790097789 date "2018-05-01" @default.
• W2790097789 modified "2023-10-12" @default.
• W2790097789 title "Sample selection via angular distance in the space of the arguments of an artificial neural network" @default.
• W2790097789 cites W1990603278 @default.
• W2790097789 cites W2016043834 @default.
• W2790097789 cites W2032969363 @default.
• W2790097789 cites W2041570644 @default.
• W2790097789 cites W2050952224 @default.
• W2790097789 cites W2056646884 @default.
• W2790097789 cites W2063983072 @default.
• W2790097789 cites W2065105535 @default.
• W2790097789 cites W2069360745 @default.
• W2790097789 cites W2102385461 @default.
• W2790097789 cites W2117873847 @default.
• W2790097789 cites W2190225614 @default.
• W2790097789 cites W2251599489 @default.
• W2790097789 doi "https://doi.org/10.1016/j.cageo.2018.02.003" @default.
• W2790097789 hasPublicationYear "2018" @default.
• W2790097789 type Work @default.
• W2790097789 sameAs 2790097789 @default.
• W2790097789 citedByCount "11" @default.
• W2790097789 countsByYear W27900977892019 @default.
• W2790097789 countsByYear W27900977892021 @default.
• W2790097789 countsByYear W27900977892022 @default.
• W2790097789 countsByYear W27900977892023 @default.
• W2790097789 crossrefType "journal-article" @default.
• W2790097789 hasAuthorship W2790097789A5027742375 @default.
• W2790097789 hasAuthorship W2790097789A5067966144 @default.
• W2790097789 hasConcept C100279318 @default.
• W2790097789 hasConcept C111335779 @default.
• W2790097789 hasConcept C111919701 @default.
• W2790097789 hasConcept C11413529 @default.
• W2790097789 hasConcept C124101348 @default.
• W2790097789 hasConcept C134306372 @default.
• W2790097789 hasConcept C153180895 @default.
• W2790097789 hasConcept C154945302 @default.
• W2790097789 hasConcept C177148314 @default.
• W2790097789 hasConcept C177264268 @default.
• W2790097789 hasConcept C185592680 @default.
• W2790097789 hasConcept C1862650 @default.
• W2790097789 hasConcept C198531522 @default.
• W2790097789 hasConcept C199360897 @default.
• W2790097789 hasConcept C2524010 @default.
• W2790097789 hasConcept C2778534509 @default.
• W2790097789 hasConcept C2781054738 @default.
• W2790097789 hasConcept C33923547 @default.
• W2790097789 hasConcept C41008148 @default.
• W2790097789 hasConcept C43617362 @default.
• W2790097789 hasConcept C50644808 @default.
• W2790097789 hasConcept C71924100 @default.
• W2790097789 hasConcept C73555534 @default.
• W2790097789 hasConcept C81917197 @default.
• W2790097789 hasConcept C98045186 @default.
• W2790097789 hasConceptScore W2790097789C100279318 @default.
• W2790097789 hasConceptScore W2790097789C111335779 @default.
• W2790097789 hasConceptScore W2790097789C111919701 @default.
• W2790097789 hasConceptScore W2790097789C11413529 @default.
• W2790097789 hasConceptScore W2790097789C124101348 @default.
• W2790097789 hasConceptScore W2790097789C134306372 @default.
• W2790097789 hasConceptScore W2790097789C153180895 @default.
• W2790097789 hasConceptScore W2790097789C154945302 @default.
• W2790097789 hasConceptScore W2790097789C177148314 @default.
• W2790097789 hasConceptScore W2790097789C177264268 @default.
• W2790097789 hasConceptScore W2790097789C185592680 @default.
• W2790097789 hasConceptScore W2790097789C1862650 @default.
• W2790097789 hasConceptScore W2790097789C198531522 @default.
• W2790097789 hasConceptScore W2790097789C199360897 @default.
• W2790097789 hasConceptScore W2790097789C2524010 @default.
• W2790097789 hasConceptScore W2790097789C2778534509 @default.
• W2790097789 hasConceptScore W2790097789C2781054738 @default.
• W2790097789 hasConceptScore W2790097789C33923547 @default.
• W2790097789 hasConceptScore W2790097789C41008148 @default.
• W2790097789 hasConceptScore W2790097789C43617362 @default.
• W2790097789 hasConceptScore W2790097789C50644808 @default.
• W2790097789 hasConceptScore W2790097789C71924100 @default.
• W2790097789 hasConceptScore W2790097789C73555534 @default.
• W2790097789 hasConceptScore W2790097789C81917197 @default.
• W2790097789 hasConceptScore W2790097789C98045186 @default.
• W2790097789 hasLocation W27900977891 @default.
• W2790097789 hasOpenAccess W2790097789 @default.
• W2790097789 hasPrimaryLocation W27900977891 @default.
• W2790097789 hasRelatedWork W2046600183 @default.
• W2790097789 hasRelatedWork W205267674 @default.
• W2790097789 hasRelatedWork W2065110043 @default.
• W2790097789 hasRelatedWork W2130825577 @default.
• W2790097789 hasRelatedWork W2345895352 @default.
• W2790097789 hasRelatedWork W2947435317 @default.
• W2790097789 hasRelatedWork W3047221865 @default.
• W2790097789 hasRelatedWork W641331424 @default.
• W2790097789 hasRelatedWork W2186435175 @default.
• W2790097789 hasRelatedWork W2339864240 @default.
• W2790097789 hasVolume "114" @default.
• W2790097789 isParatext "false" @default.
• W2790097789 isRetracted "false" @default.

• next