FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3181465667> ?p ?o ?g. }

• W3181465667 endingPage "50" @default.
• W3181465667 startingPage "40" @default.
• W3181465667 abstract "This paper considers a model of object recognition in images using convolutional neural networks; the efficiency of the model-based process involving the training of deep layers in convolutional neural networks has been studied. There are objective difficulties associated with determining the optimal characteristics of neural networks, so there is an issue related to retraining a neural network. Eliminating the retraining by determining only the optimal number of epochs is insufficient since it does not provide high accuracy. The requirements for the set of images for model training and verification have been defined. These requirements are better met by the INRIA image set (France). GoogLeNet (USA) has been established to be a trained model that can perform object recognition on images but the object recognition reliability is insufficient. Therefore, it becomes necessary to improve the effectiveness of object recognition in images. It is advisable to use the GoogLeNet architecture to build a specialized model that, by changing the parameters and retraining some layers, could allow for better recognition of objects in images. Ten models were trained using the following parameters: learning speed, the number of epochs, an optimization algorithm, the type of learning speed change, a gamma or power coefficient, a pre-trained model. A convolutional neural network has been developed to improve the precision and efficiency of object recognition in images. The optimal neural network training parameters were determined: training speed, 0.000025; the number of epochs, 100; a power coefficient, 0.25, etc. A 3 % increase in precision was obtained, which makes it possible to assert the proper choice of the architecture for the developed network and the selection of its parameters. That allows this network to be used for practical tasks of object recognition in images." @default.
• W3181465667 created "2021-07-19" @default.
• W3181465667 creator A5014004525 @default.
• W3181465667 creator A5062592166 @default.
• W3181465667 date "2021-06-30" @default.
• W3181465667 modified "2023-09-26" @default.
• W3181465667 title "Improving a model of object recognition in images based on a convolutional neural network" @default.
• W3181465667 cites W1578026398 @default.
• W3181465667 cites W1686810756 @default.
• W3181465667 cites W1849277567 @default.
• W3181465667 cites W2097117768 @default.
• W3181465667 cites W2150755264 @default.
• W3181465667 cites W2163605009 @default.
• W3181465667 cites W2164598857 @default.
• W3181465667 cites W2609402060 @default.
• W3181465667 cites W2619516334 @default.
• W3181465667 cites W2766942241 @default.
• W3181465667 cites W2891214000 @default.
• W3181465667 cites W2950476788 @default.
• W3181465667 cites W2962685937 @default.
• W3181465667 cites W2963037989 @default.
• W3181465667 cites W2964121744 @default.
• W3181465667 cites W3087594737 @default.
• W3181465667 cites W3119713086 @default.
• W3181465667 cites W3162101521 @default.
• W3181465667 doi "https://doi.org/10.15587/1729-4061.2021.233786" @default.
• W3181465667 hasPublicationYear "2021" @default.
• W3181465667 type Work @default.
• W3181465667 sameAs 3181465667 @default.
• W3181465667 citedByCount "3" @default.
• W3181465667 countsByYear W31814656672021 @default.
• W3181465667 countsByYear W31814656672022 @default.
• W3181465667 crossrefType "journal-article" @default.
• W3181465667 hasAuthorship W3181465667A5014004525 @default.
• W3181465667 hasAuthorship W3181465667A5062592166 @default.
• W3181465667 hasBestOaLocation W31814656672 @default.
• W3181465667 hasConcept C108583219 @default.
• W3181465667 hasConcept C111919701 @default.
• W3181465667 hasConcept C119857082 @default.
• W3181465667 hasConcept C121332964 @default.
• W3181465667 hasConcept C144133560 @default.
• W3181465667 hasConcept C153180895 @default.
• W3181465667 hasConcept C154945302 @default.
• W3181465667 hasConcept C155202549 @default.
• W3181465667 hasConcept C163258240 @default.
• W3181465667 hasConcept C177264268 @default.
• W3181465667 hasConcept C199360897 @default.
• W3181465667 hasConcept C2778712577 @default.
• W3181465667 hasConcept C2781238097 @default.
• W3181465667 hasConcept C31972630 @default.
• W3181465667 hasConcept C41008148 @default.
• W3181465667 hasConcept C43214815 @default.
• W3181465667 hasConcept C50644808 @default.
• W3181465667 hasConcept C62520636 @default.
• W3181465667 hasConcept C64876066 @default.
• W3181465667 hasConcept C81363708 @default.
• W3181465667 hasConcept C98045186 @default.
• W3181465667 hasConceptScore W3181465667C108583219 @default.
• W3181465667 hasConceptScore W3181465667C111919701 @default.
• W3181465667 hasConceptScore W3181465667C119857082 @default.
• W3181465667 hasConceptScore W3181465667C121332964 @default.
• W3181465667 hasConceptScore W3181465667C144133560 @default.
• W3181465667 hasConceptScore W3181465667C153180895 @default.
• W3181465667 hasConceptScore W3181465667C154945302 @default.
• W3181465667 hasConceptScore W3181465667C155202549 @default.
• W3181465667 hasConceptScore W3181465667C163258240 @default.
• W3181465667 hasConceptScore W3181465667C177264268 @default.
• W3181465667 hasConceptScore W3181465667C199360897 @default.
• W3181465667 hasConceptScore W3181465667C2778712577 @default.
• W3181465667 hasConceptScore W3181465667C2781238097 @default.
• W3181465667 hasConceptScore W3181465667C31972630 @default.
• W3181465667 hasConceptScore W3181465667C41008148 @default.
• W3181465667 hasConceptScore W3181465667C43214815 @default.
• W3181465667 hasConceptScore W3181465667C50644808 @default.
• W3181465667 hasConceptScore W3181465667C62520636 @default.
• W3181465667 hasConceptScore W3181465667C64876066 @default.
• W3181465667 hasConceptScore W3181465667C81363708 @default.
• W3181465667 hasConceptScore W3181465667C98045186 @default.
• W3181465667 hasIssue "9(111)" @default.
• W3181465667 hasLocation W31814656671 @default.
• W3181465667 hasLocation W31814656672 @default.
• W3181465667 hasLocation W31814656673 @default.
• W3181465667 hasOpenAccess W3181465667 @default.
• W3181465667 hasPrimaryLocation W31814656671 @default.
• W3181465667 hasRelatedWork W1837097281 @default.
• W3181465667 hasRelatedWork W2143500446 @default.
• W3181465667 hasRelatedWork W2200925278 @default.
• W3181465667 hasRelatedWork W2360875750 @default.
• W3181465667 hasRelatedWork W2363840281 @default.
• W3181465667 hasRelatedWork W2574146284 @default.
• W3181465667 hasRelatedWork W2613077666 @default.
• W3181465667 hasRelatedWork W2801801420 @default.
• W3181465667 hasRelatedWork W2808506981 @default.
• W3181465667 hasRelatedWork W4206120980 @default.
• W3181465667 hasVolume "3" @default.
• W3181465667 isParatext "false" @default.
• W3181465667 isRetracted "false" @default.
• W3181465667 magId "3181465667" @default.

• next