Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135841153> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3135841153 abstract "Convolutional neural networks (CNNs) have been used in many machine learning fields. In practical applications, the computational cost of convolutional neural networks is often high with the deepening of the network and the growth of data volume, mostly due to a large amount of multiplication operations of floating-point numbers in convolution operations. To reduce the amount of multiplications, we propose a new type of CNNs called Tropical Convolutional Neural Networks (TCNNs) which are built on tropical convolutions in which the multiplications and additions in conventional convolutional layers are replaced by additions and min/max operations respectively. In addition, since tropical convolution operators are essentially nonlinear operators, we expect TCNNs to have higher nonlinear fitting ability than conventional CNNs. In the experiments, we test and analyze several different architectures of TCNNs for image classification tasks in comparison with similar-sized conventional CNNs. The results show that TCNN can achieve higher expressive power than ordinary convolutional layers on the MNIST and CIFAR10 image data set. In different noise environments, there are wins and losses in the robustness of TCNN and ordinary CNNs." @default.
- W3135841153 created "2021-03-15" @default.
- W3135841153 creator A5014359523 @default.
- W3135841153 creator A5057340051 @default.
- W3135841153 creator A5074656322 @default.
- W3135841153 date "2021-03-02" @default.
- W3135841153 modified "2023-09-23" @default.
- W3135841153 title "An Alternative Practice of Tropical Convolution to Traditional Convolutional Neural Networks" @default.
- W3135841153 cites W2141125852 @default.
- W3135841153 cites W2144172034 @default.
- W3135841153 cites W2150341604 @default.
- W3135841153 cites W2153867167 @default.
- W3135841153 cites W2156877154 @default.
- W3135841153 cites W2171067922 @default.
- W3135841153 cites W2267635276 @default.
- W3135841153 cites W2300242332 @default.
- W3135841153 cites W2763160469 @default.
- W3135841153 cites W2770456481 @default.
- W3135841153 cites W2891950293 @default.
- W3135841153 cites W2962872526 @default.
- W3135841153 cites W2963114950 @default.
- W3135841153 cites W2964241181 @default.
- W3135841153 cites W3012189484 @default.
- W3135841153 cites W3034344052 @default.
- W3135841153 cites W3120434317 @default.
- W3135841153 cites W3129327024 @default.
- W3135841153 doi "https://doi.org/10.48550/arxiv.2103.02096" @default.
- W3135841153 hasPublicationYear "2021" @default.
- W3135841153 type Work @default.
- W3135841153 sameAs 3135841153 @default.
- W3135841153 citedByCount "0" @default.
- W3135841153 crossrefType "posted-content" @default.
- W3135841153 hasAuthorship W3135841153A5014359523 @default.
- W3135841153 hasAuthorship W3135841153A5057340051 @default.
- W3135841153 hasAuthorship W3135841153A5074656322 @default.
- W3135841153 hasBestOaLocation W31358411531 @default.
- W3135841153 hasConcept C104317684 @default.
- W3135841153 hasConcept C108583219 @default.
- W3135841153 hasConcept C114614502 @default.
- W3135841153 hasConcept C115961682 @default.
- W3135841153 hasConcept C121332964 @default.
- W3135841153 hasConcept C153180895 @default.
- W3135841153 hasConcept C154945302 @default.
- W3135841153 hasConcept C158622935 @default.
- W3135841153 hasConcept C185592680 @default.
- W3135841153 hasConcept C190502265 @default.
- W3135841153 hasConcept C2780595030 @default.
- W3135841153 hasConcept C33923547 @default.
- W3135841153 hasConcept C41008148 @default.
- W3135841153 hasConcept C45347329 @default.
- W3135841153 hasConcept C50644808 @default.
- W3135841153 hasConcept C55493867 @default.
- W3135841153 hasConcept C62520636 @default.
- W3135841153 hasConcept C63479239 @default.
- W3135841153 hasConcept C75294576 @default.
- W3135841153 hasConcept C81363708 @default.
- W3135841153 hasConceptScore W3135841153C104317684 @default.
- W3135841153 hasConceptScore W3135841153C108583219 @default.
- W3135841153 hasConceptScore W3135841153C114614502 @default.
- W3135841153 hasConceptScore W3135841153C115961682 @default.
- W3135841153 hasConceptScore W3135841153C121332964 @default.
- W3135841153 hasConceptScore W3135841153C153180895 @default.
- W3135841153 hasConceptScore W3135841153C154945302 @default.
- W3135841153 hasConceptScore W3135841153C158622935 @default.
- W3135841153 hasConceptScore W3135841153C185592680 @default.
- W3135841153 hasConceptScore W3135841153C190502265 @default.
- W3135841153 hasConceptScore W3135841153C2780595030 @default.
- W3135841153 hasConceptScore W3135841153C33923547 @default.
- W3135841153 hasConceptScore W3135841153C41008148 @default.
- W3135841153 hasConceptScore W3135841153C45347329 @default.
- W3135841153 hasConceptScore W3135841153C50644808 @default.
- W3135841153 hasConceptScore W3135841153C55493867 @default.
- W3135841153 hasConceptScore W3135841153C62520636 @default.
- W3135841153 hasConceptScore W3135841153C63479239 @default.
- W3135841153 hasConceptScore W3135841153C75294576 @default.
- W3135841153 hasConceptScore W3135841153C81363708 @default.
- W3135841153 hasLocation W31358411531 @default.
- W3135841153 hasOpenAccess W3135841153 @default.
- W3135841153 hasPrimaryLocation W31358411531 @default.
- W3135841153 hasRelatedWork W2167735388 @default.
- W3135841153 hasRelatedWork W2529764055 @default.
- W3135841153 hasRelatedWork W2732542196 @default.
- W3135841153 hasRelatedWork W2738221750 @default.
- W3135841153 hasRelatedWork W2766604260 @default.
- W3135841153 hasRelatedWork W2806586267 @default.
- W3135841153 hasRelatedWork W4309224979 @default.
- W3135841153 hasRelatedWork W4312417841 @default.
- W3135841153 hasRelatedWork W4317374280 @default.
- W3135841153 hasRelatedWork W564581980 @default.
- W3135841153 isParatext "false" @default.
- W3135841153 isRetracted "false" @default.
- W3135841153 magId "3135841153" @default.
- W3135841153 workType "article" @default.