Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317383327> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4317383327 abstract "Handwritten digit recognition has been widely researched. Numerous classification methods have been proposed. This article improves the recognition of handwritten numbers method based on CNN neural network. Recognition of handwritten digits has made great progress, but due to insufficient recognition accuracy, it will have a certain impact on work efficiency. In this paper, a two-layer CNN network with two fully connected layers can achieve a good prediction performance. In our framework, the activation function used is the ReLU function, to some extent, this avoids the difficulties of gradient disappearance and gradient saturation. At the same time, dropout is added to the full connection layer to discard the neurons in the network with a certain probability, which can avoid certain accidents, and the final trained network will be more robust and the generalization performance will be stronger. This method effectively improves the accuracy of recognition in the final experiment, which achieves 98.75% accuracy on theMNIST dataset and 99.25% on the CIFAR-100 dataset." @default.
- W4317383327 created "2023-01-19" @default.
- W4317383327 creator A5042978732 @default.
- W4317383327 creator A5054284198 @default.
- W4317383327 creator A5061620515 @default.
- W4317383327 creator A5089130879 @default.
- W4317383327 date "2022-12-11" @default.
- W4317383327 modified "2023-09-26" @default.
- W4317383327 title "Handwritten Digit Recognition using Deep Learning Networks" @default.
- W4317383327 cites W2194775991 @default.
- W4317383327 cites W2892341857 @default.
- W4317383327 cites W2919115771 @default.
- W4317383327 cites W2942231644 @default.
- W4317383327 cites W2966275995 @default.
- W4317383327 cites W3000371668 @default.
- W4317383327 cites W3013133070 @default.
- W4317383327 doi "https://doi.org/10.1109/tocs56154.2022.10016012" @default.
- W4317383327 hasPublicationYear "2022" @default.
- W4317383327 type Work @default.
- W4317383327 citedByCount "1" @default.
- W4317383327 countsByYear W43173833272023 @default.
- W4317383327 crossrefType "proceedings-article" @default.
- W4317383327 hasAuthorship W4317383327A5042978732 @default.
- W4317383327 hasAuthorship W4317383327A5054284198 @default.
- W4317383327 hasAuthorship W4317383327A5061620515 @default.
- W4317383327 hasAuthorship W4317383327A5089130879 @default.
- W4317383327 hasConcept C112640561 @default.
- W4317383327 hasConcept C119857082 @default.
- W4317383327 hasConcept C134306372 @default.
- W4317383327 hasConcept C14036430 @default.
- W4317383327 hasConcept C153180895 @default.
- W4317383327 hasConcept C154945302 @default.
- W4317383327 hasConcept C177148314 @default.
- W4317383327 hasConcept C2776145597 @default.
- W4317383327 hasConcept C28490314 @default.
- W4317383327 hasConcept C2984784707 @default.
- W4317383327 hasConcept C33923547 @default.
- W4317383327 hasConcept C38365724 @default.
- W4317383327 hasConcept C41008148 @default.
- W4317383327 hasConcept C50644808 @default.
- W4317383327 hasConcept C52622490 @default.
- W4317383327 hasConcept C78458016 @default.
- W4317383327 hasConcept C86803240 @default.
- W4317383327 hasConceptScore W4317383327C112640561 @default.
- W4317383327 hasConceptScore W4317383327C119857082 @default.
- W4317383327 hasConceptScore W4317383327C134306372 @default.
- W4317383327 hasConceptScore W4317383327C14036430 @default.
- W4317383327 hasConceptScore W4317383327C153180895 @default.
- W4317383327 hasConceptScore W4317383327C154945302 @default.
- W4317383327 hasConceptScore W4317383327C177148314 @default.
- W4317383327 hasConceptScore W4317383327C2776145597 @default.
- W4317383327 hasConceptScore W4317383327C28490314 @default.
- W4317383327 hasConceptScore W4317383327C2984784707 @default.
- W4317383327 hasConceptScore W4317383327C33923547 @default.
- W4317383327 hasConceptScore W4317383327C38365724 @default.
- W4317383327 hasConceptScore W4317383327C41008148 @default.
- W4317383327 hasConceptScore W4317383327C50644808 @default.
- W4317383327 hasConceptScore W4317383327C52622490 @default.
- W4317383327 hasConceptScore W4317383327C78458016 @default.
- W4317383327 hasConceptScore W4317383327C86803240 @default.
- W4317383327 hasLocation W43173833271 @default.
- W4317383327 hasOpenAccess W4317383327 @default.
- W4317383327 hasPrimaryLocation W43173833271 @default.
- W4317383327 hasRelatedWork W2139588461 @default.
- W4317383327 hasRelatedWork W2280383998 @default.
- W4317383327 hasRelatedWork W2367193181 @default.
- W4317383327 hasRelatedWork W2963070594 @default.
- W4317383327 hasRelatedWork W2989932438 @default.
- W4317383327 hasRelatedWork W3005627584 @default.
- W4317383327 hasRelatedWork W3128220493 @default.
- W4317383327 hasRelatedWork W4280592718 @default.
- W4317383327 hasRelatedWork W1629725936 @default.
- W4317383327 hasRelatedWork W4287869072 @default.
- W4317383327 isParatext "false" @default.
- W4317383327 isRetracted "false" @default.
- W4317383327 workType "article" @default.