Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912457210> ?p ?o ?g. }
- W2912457210 endingPage "411" @default.
- W2912457210 startingPage "397" @default.
- W2912457210 abstract "The present paper aims to show the necessity of information augmentation to cope with the natural decrease in information content in multi-layered neural networks. It is natural to make an effort to collect as much information as possible, because it is impossible to know which information is necessary or useful before learning. Thus, the present paper tries to force neural networks to form new network configurations to have as much information as possible, contrary to the conventional approach of information reduction, such as many types of regularization. For information augmentation, we use the self-organizing map (SOM), which can over-represent inputs and produce as many similar weights as possible. The method was applied to two data sets: the banknote authentication data set and the character recognition data set. In both experimental results, it was confirmed that redundant and excessive information generation in terms of the excessive number of connection weights was connected with improved generalization." @default.
- W2912457210 created "2019-02-21" @default.
- W2912457210 creator A5079603834 @default.
- W2912457210 date "2019-07-01" @default.
- W2912457210 modified "2023-10-17" @default.
- W2912457210 title "SOM-based information maximization to improve and interpret multi-layered neural networks: From information reduction to information augmentation approach to create new information" @default.
- W2912457210 cites W1086688568 @default.
- W2912457210 cites W1588337522 @default.
- W2912457210 cites W1979812372 @default.
- W2912457210 cites W1986178142 @default.
- W2912457210 cites W1989049108 @default.
- W2912457210 cites W1990517717 @default.
- W2912457210 cites W1990606352 @default.
- W2912457210 cites W1990895816 @default.
- W2912457210 cites W2051810070 @default.
- W2912457210 cites W2057041027 @default.
- W2912457210 cites W2063046703 @default.
- W2912457210 cites W2069143585 @default.
- W2912457210 cites W2070955875 @default.
- W2912457210 cites W2076063813 @default.
- W2912457210 cites W2094015382 @default.
- W2912457210 cites W2094558429 @default.
- W2912457210 cites W2096352448 @default.
- W2912457210 cites W2098969718 @default.
- W2912457210 cites W2100005846 @default.
- W2912457210 cites W2100495367 @default.
- W2912457210 cites W2101938621 @default.
- W2912457210 cites W2102131386 @default.
- W2912457210 cites W2105464873 @default.
- W2912457210 cites W2107878631 @default.
- W2912457210 cites W2110464958 @default.
- W2912457210 cites W2119290563 @default.
- W2912457210 cites W2122389322 @default.
- W2912457210 cites W2122925692 @default.
- W2912457210 cites W2123806929 @default.
- W2912457210 cites W2127842029 @default.
- W2912457210 cites W2139094401 @default.
- W2912457210 cites W2144212877 @default.
- W2912457210 cites W2144354855 @default.
- W2912457210 cites W2144914634 @default.
- W2912457210 cites W2148394752 @default.
- W2912457210 cites W2151345721 @default.
- W2912457210 cites W2151616049 @default.
- W2912457210 cites W2159178073 @default.
- W2912457210 cites W2167541154 @default.
- W2912457210 cites W2911964244 @default.
- W2912457210 cites W2962689739 @default.
- W2912457210 cites W3123606858 @default.
- W2912457210 cites W4212883601 @default.
- W2912457210 cites W4238179892 @default.
- W2912457210 cites W81573328 @default.
- W2912457210 doi "https://doi.org/10.1016/j.eswa.2019.01.056" @default.
- W2912457210 hasPublicationYear "2019" @default.
- W2912457210 type Work @default.
- W2912457210 sameAs 2912457210 @default.
- W2912457210 citedByCount "11" @default.
- W2912457210 countsByYear W29124572102019 @default.
- W2912457210 countsByYear W29124572102020 @default.
- W2912457210 countsByYear W29124572102021 @default.
- W2912457210 countsByYear W29124572102022 @default.
- W2912457210 crossrefType "journal-article" @default.
- W2912457210 hasAuthorship W2912457210A5079603834 @default.
- W2912457210 hasConcept C111335779 @default.
- W2912457210 hasConcept C119857082 @default.
- W2912457210 hasConcept C124101348 @default.
- W2912457210 hasConcept C126255220 @default.
- W2912457210 hasConcept C134306372 @default.
- W2912457210 hasConcept C154945302 @default.
- W2912457210 hasConcept C177148314 @default.
- W2912457210 hasConcept C177264268 @default.
- W2912457210 hasConcept C199360897 @default.
- W2912457210 hasConcept C2524010 @default.
- W2912457210 hasConcept C2776330181 @default.
- W2912457210 hasConcept C33923547 @default.
- W2912457210 hasConcept C41008148 @default.
- W2912457210 hasConcept C50644808 @default.
- W2912457210 hasConceptScore W2912457210C111335779 @default.
- W2912457210 hasConceptScore W2912457210C119857082 @default.
- W2912457210 hasConceptScore W2912457210C124101348 @default.
- W2912457210 hasConceptScore W2912457210C126255220 @default.
- W2912457210 hasConceptScore W2912457210C134306372 @default.
- W2912457210 hasConceptScore W2912457210C154945302 @default.
- W2912457210 hasConceptScore W2912457210C177148314 @default.
- W2912457210 hasConceptScore W2912457210C177264268 @default.
- W2912457210 hasConceptScore W2912457210C199360897 @default.
- W2912457210 hasConceptScore W2912457210C2524010 @default.
- W2912457210 hasConceptScore W2912457210C2776330181 @default.
- W2912457210 hasConceptScore W2912457210C33923547 @default.
- W2912457210 hasConceptScore W2912457210C41008148 @default.
- W2912457210 hasConceptScore W2912457210C50644808 @default.
- W2912457210 hasFunder F4320334764 @default.
- W2912457210 hasLocation W29124572101 @default.
- W2912457210 hasOpenAccess W2912457210 @default.
- W2912457210 hasPrimaryLocation W29124572101 @default.
- W2912457210 hasRelatedWork W2366092068 @default.
- W2912457210 hasRelatedWork W2961085424 @default.
- W2912457210 hasRelatedWork W2989932438 @default.
- W2912457210 hasRelatedWork W3090337104 @default.