Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765648979> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2765648979 endingPage "64" @default.
- W2765648979 startingPage "59" @default.
- W2765648979 abstract "Background. A significant drawback of the technology of creating modern neural network models based on the multilayer perceptron is that when the parameters of the case studies are encoded, the expected output signal correlation with the similarity of the class standards to be recognized is not taken into account.Objective. The aim of the paper is the development of the method for encoding the output of the case studies, which ensures the reflection of the similarity of the class standards to be recognized.Methods. The encoding method is based on a probabilistic neural network, in which case studies the expected output signal is determined not by numerical form but by the class name to be recognized. At the same time, when recognizing, it is possible in the numerical form of the output signal of the network to show the similarity of the input image to each class that was laid in it during the training.Results. The encoding method has been developed, which, due to the use of the probabilistic neural network, allows us to consider the similarity of the class standards to be recognized in the expected output signal of the case studies.Conclusions. The proposed method allows reducing the number of training iterations 1.3–1.5 times to achieve a tolerable learning error within 1 %." @default.
- W2765648979 created "2017-11-10" @default.
- W2765648979 creator A5029556742 @default.
- W2765648979 creator A5030818098 @default.
- W2765648979 date "2017-10-31" @default.
- W2765648979 modified "2023-09-30" @default.
- W2765648979 title "Method of Encoding the Output Signal of Neural Networks Models" @default.
- W2765648979 cites W1951742130 @default.
- W2765648979 cites W2963355447 @default.
- W2765648979 cites W2964199361 @default.
- W2765648979 cites W2964325005 @default.
- W2765648979 cites W2979246476 @default.
- W2765648979 doi "https://doi.org/10.20535/1810-0546.2017.5.107206" @default.
- W2765648979 hasPublicationYear "2017" @default.
- W2765648979 type Work @default.
- W2765648979 sameAs 2765648979 @default.
- W2765648979 citedByCount "0" @default.
- W2765648979 crossrefType "journal-article" @default.
- W2765648979 hasAuthorship W2765648979A5029556742 @default.
- W2765648979 hasAuthorship W2765648979A5030818098 @default.
- W2765648979 hasBestOaLocation W27656489791 @default.
- W2765648979 hasConcept C103278499 @default.
- W2765648979 hasConcept C11413529 @default.
- W2765648979 hasConcept C115961682 @default.
- W2765648979 hasConcept C119857082 @default.
- W2765648979 hasConcept C124101348 @default.
- W2765648979 hasConcept C125411270 @default.
- W2765648979 hasConcept C134342201 @default.
- W2765648979 hasConcept C153180895 @default.
- W2765648979 hasConcept C154945302 @default.
- W2765648979 hasConcept C175202392 @default.
- W2765648979 hasConcept C199360897 @default.
- W2765648979 hasConcept C2777212361 @default.
- W2765648979 hasConcept C2779843651 @default.
- W2765648979 hasConcept C41008148 @default.
- W2765648979 hasConcept C49937458 @default.
- W2765648979 hasConcept C50644808 @default.
- W2765648979 hasConcept C60908668 @default.
- W2765648979 hasConceptScore W2765648979C103278499 @default.
- W2765648979 hasConceptScore W2765648979C11413529 @default.
- W2765648979 hasConceptScore W2765648979C115961682 @default.
- W2765648979 hasConceptScore W2765648979C119857082 @default.
- W2765648979 hasConceptScore W2765648979C124101348 @default.
- W2765648979 hasConceptScore W2765648979C125411270 @default.
- W2765648979 hasConceptScore W2765648979C134342201 @default.
- W2765648979 hasConceptScore W2765648979C153180895 @default.
- W2765648979 hasConceptScore W2765648979C154945302 @default.
- W2765648979 hasConceptScore W2765648979C175202392 @default.
- W2765648979 hasConceptScore W2765648979C199360897 @default.
- W2765648979 hasConceptScore W2765648979C2777212361 @default.
- W2765648979 hasConceptScore W2765648979C2779843651 @default.
- W2765648979 hasConceptScore W2765648979C41008148 @default.
- W2765648979 hasConceptScore W2765648979C49937458 @default.
- W2765648979 hasConceptScore W2765648979C50644808 @default.
- W2765648979 hasConceptScore W2765648979C60908668 @default.
- W2765648979 hasIssue "5" @default.
- W2765648979 hasLocation W27656489791 @default.
- W2765648979 hasLocation W27656489792 @default.
- W2765648979 hasOpenAccess W2765648979 @default.
- W2765648979 hasPrimaryLocation W27656489791 @default.
- W2765648979 hasRelatedWork W1975643538 @default.
- W2765648979 hasRelatedWork W2067837718 @default.
- W2765648979 hasRelatedWork W2236741694 @default.
- W2765648979 hasRelatedWork W2355766745 @default.
- W2765648979 hasRelatedWork W2366803925 @default.
- W2765648979 hasRelatedWork W2375446027 @default.
- W2765648979 hasRelatedWork W2380307146 @default.
- W2765648979 hasRelatedWork W2381770184 @default.
- W2765648979 hasRelatedWork W4294967761 @default.
- W2765648979 hasRelatedWork W611222296 @default.
- W2765648979 hasVolume "0" @default.
- W2765648979 isParatext "false" @default.
- W2765648979 isRetracted "false" @default.
- W2765648979 magId "2765648979" @default.
- W2765648979 workType "article" @default.