FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207851878> ?p ?o ?g. }

• W3207851878 abstract "Abstract The focus of this work is on the application of classical Model Order Reduction techniques, such as Active Subspaces and Proper Orthogonal Decomposition, to Deep Neural Networks. We propose a generic methodology to reduce the number of layers in a pre-trained network by combining the aforementioned techniques for dimensionality reduction with input-output mappings, such as Polynomial Chaos Expansion and Feedforward Neural Networks. The motivation behind compressing the architecture of an existing Convolutional Neural Network arises from its usage in embedded systems with specific storage constraints. The conducted numerical tests demonstrate that the resulting reduced networks can achieve a level of accuracy comparable to the original Convolutional Neural Network being examined, while also saving memory allocation. Our primary emphasis lies in the field of image recognition, where we tested our methodology using VGG-16 and ResNet-110 architectures against three different datasets: CIFAR-10, CIFAR-100, and a custom dataset." @default.
• W3207851878 created "2021-10-25" @default.
• W3207851878 creator A5043599485 @default.
• W3207851878 creator A5061558433 @default.
• W3207851878 creator A5077743159 @default.
• W3207851878 date "2023-07-04" @default.
• W3207851878 modified "2023-10-03" @default.
• W3207851878 title "A dimensionality reduction approach for convolutional neural networks" @default.
• W3207851878 cites W1485437584 @default.
• W3207851878 cites W1538934584 @default.
• W3207851878 cites W1965847964 @default.
• W3207851878 cites W2018159038 @default.
• W3207851878 cites W2049774453 @default.
• W3207851878 cites W2088335308 @default.
• W3207851878 cites W2103559015 @default.
• W3207851878 cites W2116386142 @default.
• W3207851878 cites W2133041109 @default.
• W3207851878 cites W2147836374 @default.
• W3207851878 cites W2194775991 @default.
• W3207851878 cites W2267573953 @default.
• W3207851878 cites W2321957512 @default.
• W3207851878 cites W2333312111 @default.
• W3207851878 cites W2516041031 @default.
• W3207851878 cites W2617994470 @default.
• W3207851878 cites W2618530766 @default.
• W3207851878 cites W2747680751 @default.
• W3207851878 cites W2766267279 @default.
• W3207851878 cites W2884001105 @default.
• W3207851878 cites W2897295818 @default.
• W3207851878 cites W2930581984 @default.
• W3207851878 cites W2962851801 @default.
• W3207851878 cites W2962939807 @default.
• W3207851878 cites W2962949934 @default.
• W3207851878 cites W2963363373 @default.
• W3207851878 cites W2965862774 @default.
• W3207851878 cites W2988916019 @default.
• W3207851878 cites W2989808579 @default.
• W3207851878 cites W2999803881 @default.
• W3207851878 cites W3004127093 @default.
• W3207851878 cites W3011371203 @default.
• W3207851878 cites W3012165385 @default.
• W3207851878 cites W3034368386 @default.
• W3207851878 cites W3034818206 @default.
• W3207851878 cites W3080980059 @default.
• W3207851878 cites W3095125464 @default.
• W3207851878 cites W3100321043 @default.
• W3207851878 cites W3103145119 @default.
• W3207851878 cites W3103869760 @default.
• W3207851878 cites W3127873279 @default.
• W3207851878 cites W3140854437 @default.
• W3207851878 cites W3187277596 @default.
• W3207851878 cites W3196481167 @default.
• W3207851878 cites W3199430110 @default.
• W3207851878 cites W3202145349 @default.
• W3207851878 cites W3212281303 @default.
• W3207851878 cites W3217606893 @default.
• W3207851878 cites W4206351424 @default.
• W3207851878 cites W4232619139 @default.
• W3207851878 cites W4252750892 @default.
• W3207851878 cites W4256161595 @default.
• W3207851878 cites W4288076655 @default.
• W3207851878 cites W4288083474 @default.
• W3207851878 cites W4296246261 @default.
• W3207851878 cites W4312638763 @default.
• W3207851878 cites W4312690709 @default.
• W3207851878 cites W4300578686 @default.
• W3207851878 doi "https://doi.org/10.1007/s10489-023-04730-1" @default.
• W3207851878 hasPublicationYear "2023" @default.
• W3207851878 type Work @default.
• W3207851878 sameAs 3207851878 @default.
• W3207851878 citedByCount "0" @default.
• W3207851878 crossrefType "journal-article" @default.
• W3207851878 hasAuthorship W3207851878A5043599485 @default.
• W3207851878 hasAuthorship W3207851878A5061558433 @default.
• W3207851878 hasAuthorship W3207851878A5077743159 @default.
• W3207851878 hasBestOaLocation W32078518781 @default.
• W3207851878 hasConcept C108583219 @default.
• W3207851878 hasConcept C111030470 @default.
• W3207851878 hasConcept C111335779 @default.
• W3207851878 hasConcept C153180895 @default.
• W3207851878 hasConcept C154945302 @default.
• W3207851878 hasConcept C202444582 @default.
• W3207851878 hasConcept C2524010 @default.
• W3207851878 hasConcept C26517878 @default.
• W3207851878 hasConcept C33676613 @default.
• W3207851878 hasConcept C33923547 @default.
• W3207851878 hasConcept C38652104 @default.
• W3207851878 hasConcept C41008148 @default.
• W3207851878 hasConcept C47702885 @default.
• W3207851878 hasConcept C50644808 @default.
• W3207851878 hasConcept C70518039 @default.
• W3207851878 hasConcept C81363708 @default.
• W3207851878 hasConcept C9652623 @default.
• W3207851878 hasConceptScore W3207851878C108583219 @default.
• W3207851878 hasConceptScore W3207851878C111030470 @default.
• W3207851878 hasConceptScore W3207851878C111335779 @default.
• W3207851878 hasConceptScore W3207851878C153180895 @default.
• W3207851878 hasConceptScore W3207851878C154945302 @default.
• W3207851878 hasConceptScore W3207851878C202444582 @default.
• W3207851878 hasConceptScore W3207851878C2524010 @default.

• next