Matches in SemOpenAlex for { <https://semopenalex.org/work/W2090032587> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2090032587 endingPage "67" @default.
- W2090032587 startingPage "57" @default.
- W2090032587 abstract "This paper proposes an efficient learning method for a layered neural network based on the selection of training data and the input characteristics of an output layer unit. Compared to recent neural networks, pulse neural networks, and quantum neuro computation, the multilayer neural network is widely used due to its simple structure. When learning objects are complicated, problems such as unsuccessful learning or a significant time required in learning remain unsolved. The aims of this paper are to suggest solutions for these problems and to reduce the total learning time. The total learning time means the total computational time required to learn certain objects, including adjusting parameter values and restarting learning from the beginning. Focusing on the input data during the learning stage, we undertook an experiment to identify the data that create large errors and interfere with the learning process. Our method divides the learning process into several stages. In general, the input characteristics to an output layer unit show oscillation during the learning process for complicated problems. Focusing on the oscillatory characteristics, it is determined whether the learning will move on to the next stage or the learning will restart from the beginning. Computational experiments suggest that the proposed method has the capability for higher learning performance and needs less learning time compared with the conventional method. © 2012 Wiley Periodicals, Inc. Electron Comm Jpn, 95(4): 57–67, 2012; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/ecj.10365" @default.
- W2090032587 created "2016-06-24" @default.
- W2090032587 creator A5030780411 @default.
- W2090032587 creator A5045262156 @default.
- W2090032587 date "2012-03-01" @default.
- W2090032587 modified "2023-09-24" @default.
- W2090032587 title "An efficient learning method for layered neural networks based on selection of training data and input characteristics of an output layer unit" @default.
- W2090032587 cites W1971735090 @default.
- W2090032587 cites W2090293612 @default.
- W2090032587 cites W2105641627 @default.
- W2090032587 cites W2143908786 @default.
- W2090032587 cites W2156003784 @default.
- W2090032587 doi "https://doi.org/10.1002/ecj.10365" @default.
- W2090032587 hasPublicationYear "2012" @default.
- W2090032587 type Work @default.
- W2090032587 sameAs 2090032587 @default.
- W2090032587 citedByCount "2" @default.
- W2090032587 countsByYear W20900325872013 @default.
- W2090032587 crossrefType "journal-article" @default.
- W2090032587 hasAuthorship W2090032587A5030780411 @default.
- W2090032587 hasAuthorship W2090032587A5045262156 @default.
- W2090032587 hasConcept C108583219 @default.
- W2090032587 hasConcept C111919701 @default.
- W2090032587 hasConcept C119857082 @default.
- W2090032587 hasConcept C120822770 @default.
- W2090032587 hasConcept C154945302 @default.
- W2090032587 hasConcept C178790620 @default.
- W2090032587 hasConcept C185592680 @default.
- W2090032587 hasConcept C2779227376 @default.
- W2090032587 hasConcept C34585555 @default.
- W2090032587 hasConcept C41008148 @default.
- W2090032587 hasConcept C50644808 @default.
- W2090032587 hasConcept C8038995 @default.
- W2090032587 hasConcept C98045186 @default.
- W2090032587 hasConceptScore W2090032587C108583219 @default.
- W2090032587 hasConceptScore W2090032587C111919701 @default.
- W2090032587 hasConceptScore W2090032587C119857082 @default.
- W2090032587 hasConceptScore W2090032587C120822770 @default.
- W2090032587 hasConceptScore W2090032587C154945302 @default.
- W2090032587 hasConceptScore W2090032587C178790620 @default.
- W2090032587 hasConceptScore W2090032587C185592680 @default.
- W2090032587 hasConceptScore W2090032587C2779227376 @default.
- W2090032587 hasConceptScore W2090032587C34585555 @default.
- W2090032587 hasConceptScore W2090032587C41008148 @default.
- W2090032587 hasConceptScore W2090032587C50644808 @default.
- W2090032587 hasConceptScore W2090032587C8038995 @default.
- W2090032587 hasConceptScore W2090032587C98045186 @default.
- W2090032587 hasIssue "4" @default.
- W2090032587 hasLocation W20900325871 @default.
- W2090032587 hasOpenAccess W2090032587 @default.
- W2090032587 hasPrimaryLocation W20900325871 @default.
- W2090032587 hasRelatedWork W2908875379 @default.
- W2090032587 hasRelatedWork W2956138382 @default.
- W2090032587 hasRelatedWork W3044458868 @default.
- W2090032587 hasRelatedWork W3082895349 @default.
- W2090032587 hasRelatedWork W3123344745 @default.
- W2090032587 hasRelatedWork W3133293092 @default.
- W2090032587 hasRelatedWork W3208584567 @default.
- W2090032587 hasRelatedWork W4221136938 @default.
- W2090032587 hasRelatedWork W4302303815 @default.
- W2090032587 hasRelatedWork W4309113015 @default.
- W2090032587 hasVolume "95" @default.
- W2090032587 isParatext "false" @default.
- W2090032587 isRetracted "false" @default.
- W2090032587 magId "2090032587" @default.
- W2090032587 workType "article" @default.