Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308725904> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4308725904 abstract "This paper explores a deeper network architecture diagram, which can be viewed as an enhanced version of AlexNet. In the design of the winder, a smaller winder core is used, which verifies that the small size of the winder core in the deep network can not only reduce the parameters, but also achieve better results. The concept of Inception was introduced and the idea of widening was designed under the prevailing model of deepening at that time. Moreover, two weighted Softmax branches can be conducted, which consist of two functions. One is to avoid the disappearance of the gradient, and is used for conducting the gradient forward. If one of the layers is 0 in the back propagation, the chain is 0. The second is to utilize the output layer of the middle layer as a classification to analyze the significant role in the model fusion. They decompose the convolution of the filter size NXN into a combination of 1xn and nx1 convolution. For example, 3 by 3 convolution is equivalent to first performing 1 by 3 convolution, and then performing 3 by 1 convolution on its output. They found that this method is 33% cheaper than a single 3x3 convolution." @default.
- W4308725904 created "2022-11-15" @default.
- W4308725904 creator A5018748397 @default.
- W4308725904 creator A5056674662 @default.
- W4308725904 creator A5070344630 @default.
- W4308725904 date "2022-10-11" @default.
- W4308725904 modified "2023-09-27" @default.
- W4308725904 title "Image Classification Based on a Weighted CNN Model" @default.
- W4308725904 cites W1575192016 @default.
- W4308725904 cites W2007312210 @default.
- W4308725904 cites W2037975854 @default.
- W4308725904 cites W2186500555 @default.
- W4308725904 cites W2531426067 @default.
- W4308725904 cites W2797344641 @default.
- W4308725904 cites W2887527983 @default.
- W4308725904 cites W2948768062 @default.
- W4308725904 cites W3122451732 @default.
- W4308725904 doi "https://doi.org/10.23919/wac55640.2022.9934385" @default.
- W4308725904 hasPublicationYear "2022" @default.
- W4308725904 type Work @default.
- W4308725904 citedByCount "0" @default.
- W4308725904 crossrefType "proceedings-article" @default.
- W4308725904 hasAuthorship W4308725904A5018748397 @default.
- W4308725904 hasAuthorship W4308725904A5056674662 @default.
- W4308725904 hasAuthorship W4308725904A5070344630 @default.
- W4308725904 hasConcept C106131492 @default.
- W4308725904 hasConcept C11413529 @default.
- W4308725904 hasConcept C115961682 @default.
- W4308725904 hasConcept C153180895 @default.
- W4308725904 hasConcept C154945302 @default.
- W4308725904 hasConcept C178790620 @default.
- W4308725904 hasConcept C185592680 @default.
- W4308725904 hasConcept C188441871 @default.
- W4308725904 hasConcept C2164484 @default.
- W4308725904 hasConcept C2779227376 @default.
- W4308725904 hasConcept C31972630 @default.
- W4308725904 hasConcept C41008148 @default.
- W4308725904 hasConcept C45347329 @default.
- W4308725904 hasConcept C50644808 @default.
- W4308725904 hasConcept C76155785 @default.
- W4308725904 hasConcept C81363708 @default.
- W4308725904 hasConceptScore W4308725904C106131492 @default.
- W4308725904 hasConceptScore W4308725904C11413529 @default.
- W4308725904 hasConceptScore W4308725904C115961682 @default.
- W4308725904 hasConceptScore W4308725904C153180895 @default.
- W4308725904 hasConceptScore W4308725904C154945302 @default.
- W4308725904 hasConceptScore W4308725904C178790620 @default.
- W4308725904 hasConceptScore W4308725904C185592680 @default.
- W4308725904 hasConceptScore W4308725904C188441871 @default.
- W4308725904 hasConceptScore W4308725904C2164484 @default.
- W4308725904 hasConceptScore W4308725904C2779227376 @default.
- W4308725904 hasConceptScore W4308725904C31972630 @default.
- W4308725904 hasConceptScore W4308725904C41008148 @default.
- W4308725904 hasConceptScore W4308725904C45347329 @default.
- W4308725904 hasConceptScore W4308725904C50644808 @default.
- W4308725904 hasConceptScore W4308725904C76155785 @default.
- W4308725904 hasConceptScore W4308725904C81363708 @default.
- W4308725904 hasLocation W43087259041 @default.
- W4308725904 hasOpenAccess W4308725904 @default.
- W4308725904 hasPrimaryLocation W43087259041 @default.
- W4308725904 hasRelatedWork W2743258233 @default.
- W4308725904 hasRelatedWork W2758063741 @default.
- W4308725904 hasRelatedWork W2810384904 @default.
- W4308725904 hasRelatedWork W2883041339 @default.
- W4308725904 hasRelatedWork W2977314777 @default.
- W4308725904 hasRelatedWork W3171731982 @default.
- W4308725904 hasRelatedWork W3200445080 @default.
- W4308725904 hasRelatedWork W3208883981 @default.
- W4308725904 hasRelatedWork W4307834408 @default.
- W4308725904 hasRelatedWork W4320925816 @default.
- W4308725904 isParatext "false" @default.
- W4308725904 isRetracted "false" @default.
- W4308725904 workType "article" @default.