Matches in SemOpenAlex for { <https://semopenalex.org/work/W2584957437> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2584957437 endingPage "666" @default.
- W2584957437 startingPage "663" @default.
- W2584957437 abstract "Artificial Neural Networks are often looked upon as black boxes that can be used for classification tasks. Regarding the ANN as a simple tool to do a final classification, the research efforts tend to be concentrated on preprocessing stages, to improve the quality of the input to the neural network. One such preprocessor is the MSECT algorithm by Zahorian and Jagharghi [1]. It improves vowel classification. Since MSECT applies an affine transformation to the data, it is hard to see why this should make any difference to the end result. By implementing and testing the MSECT algoritm, using a simple backpropagation neural network as a tool or standard to measure the amount of neural network training needed to correctly classify two data clusters we confirmed the results of Zahorian and Jagharghi [2]. The simple ANN we used to classify the vowel data was not that simple at all. The preprocessing algorithm changes not only the dimension but also the scale of the vowel data. To perform optimal on the original data and on the preprocessed data the ANN would need different optimal parameters. But because the parameters of the ANN were not modified this preprocessing could result in better results for one of the data sets. An experiment was done with different scalings of the same data sets. For the parameters of the ANN we used, the optimal results in terms of speed of convergence and accuracy were obtained for data scaled to have their input range between 5 and 18." @default.
- W2584957437 created "2017-02-10" @default.
- W2584957437 creator A5017213156 @default.
- W2584957437 creator A5036561254 @default.
- W2584957437 creator A5079827800 @default.
- W2584957437 date "1993-12-01" @default.
- W2584957437 modified "2023-09-23" @default.
- W2584957437 title "The Effects of Scaling on Neural Network Classification" @default.
- W2584957437 hasPublicationYear "1993" @default.
- W2584957437 type Work @default.
- W2584957437 sameAs 2584957437 @default.
- W2584957437 citedByCount "0" @default.
- W2584957437 crossrefType "journal-article" @default.
- W2584957437 hasAuthorship W2584957437A5017213156 @default.
- W2584957437 hasAuthorship W2584957437A5036561254 @default.
- W2584957437 hasAuthorship W2584957437A5079827800 @default.
- W2584957437 hasConcept C10551718 @default.
- W2584957437 hasConcept C124101348 @default.
- W2584957437 hasConcept C153180895 @default.
- W2584957437 hasConcept C154945302 @default.
- W2584957437 hasConcept C155032097 @default.
- W2584957437 hasConcept C202444582 @default.
- W2584957437 hasConcept C33676613 @default.
- W2584957437 hasConcept C33923547 @default.
- W2584957437 hasConcept C34736171 @default.
- W2584957437 hasConcept C41008148 @default.
- W2584957437 hasConcept C50644808 @default.
- W2584957437 hasConceptScore W2584957437C10551718 @default.
- W2584957437 hasConceptScore W2584957437C124101348 @default.
- W2584957437 hasConceptScore W2584957437C153180895 @default.
- W2584957437 hasConceptScore W2584957437C154945302 @default.
- W2584957437 hasConceptScore W2584957437C155032097 @default.
- W2584957437 hasConceptScore W2584957437C202444582 @default.
- W2584957437 hasConceptScore W2584957437C33676613 @default.
- W2584957437 hasConceptScore W2584957437C33923547 @default.
- W2584957437 hasConceptScore W2584957437C34736171 @default.
- W2584957437 hasConceptScore W2584957437C41008148 @default.
- W2584957437 hasConceptScore W2584957437C50644808 @default.
- W2584957437 hasOpenAccess W2584957437 @default.
- W2584957437 hasRelatedWork W1569549387 @default.
- W2584957437 hasRelatedWork W1583772825 @default.
- W2584957437 hasRelatedWork W1617445017 @default.
- W2584957437 hasRelatedWork W1629227451 @default.
- W2584957437 hasRelatedWork W1938722960 @default.
- W2584957437 hasRelatedWork W1965369676 @default.
- W2584957437 hasRelatedWork W1965757531 @default.
- W2584957437 hasRelatedWork W2059019633 @default.
- W2584957437 hasRelatedWork W2106224199 @default.
- W2584957437 hasRelatedWork W2121839474 @default.
- W2584957437 hasRelatedWork W2182600809 @default.
- W2584957437 hasRelatedWork W2278421469 @default.
- W2584957437 hasRelatedWork W2726756416 @default.
- W2584957437 hasRelatedWork W2771575470 @default.
- W2584957437 hasRelatedWork W2790097789 @default.
- W2584957437 hasRelatedWork W1009899952 @default.
- W2584957437 hasRelatedWork W1975223937 @default.
- W2584957437 hasRelatedWork W2279193159 @default.
- W2584957437 hasRelatedWork W2785180770 @default.
- W2584957437 hasRelatedWork W2966746915 @default.
- W2584957437 isParatext "false" @default.
- W2584957437 isRetracted "false" @default.
- W2584957437 magId "2584957437" @default.
- W2584957437 workType "article" @default.