Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387004586> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4387004586 endingPage "121734" @default.
- W4387004586 startingPage "121734" @default.
- W4387004586 abstract "Due to its efficient model calibration given by unique incremental learning capability, broad learning system (BLS) has made impressive progress in image analytical tasks such as image classification and object detection. Inspired by this incremental remodel success, we proposed a novel transformer-BLS network to achieve a trade-off between model training speed and accuracy. Specially, we developed sub-BLS layers with the multi-head attention mechanism and combining these layers to construct a transformer-BLS network. In particular, our proposed transformer-BLS network provides four different incremental learning algorithms that enable the proposed model can realize the increments of its feature nodes, enhancement nodes, input data and sub-BLS layers, respectively, without the need of the full-weight update in this model. Furthermore, we validated the performance of our transformer-BLS network and its four incremental learning algorithms on a variety of image classification datasets. The results demonstrated that the proposed transformer-BLS maintains classification performance on both the MNIST and Fashion-MNIST datasets, while saving 2/3 of the training time. These findings imply that the proposed method has the potential in significant reducing model training complexity with this incremental remodel system, while simultaneously improving the increment learning performance of the original BLS within such contexts, especially in the classification task of some datasets." @default.
- W4387004586 created "2023-09-26" @default.
- W4387004586 creator A5014837150 @default.
- W4387004586 creator A5028046862 @default.
- W4387004586 creator A5028910864 @default.
- W4387004586 creator A5029866745 @default.
- W4387004586 creator A5040048271 @default.
- W4387004586 creator A5043608851 @default.
- W4387004586 creator A5084817144 @default.
- W4387004586 creator A5090330947 @default.
- W4387004586 date "2024-03-01" @default.
- W4387004586 modified "2023-10-11" @default.
- W4387004586 title "Transformer-BLS: An efficient learning algorithm based on multi-head attention mechanism and incremental learning algorithms" @default.
- W4387004586 cites W2009086942 @default.
- W4387004586 cites W2012638612 @default.
- W4387004586 cites W2025768430 @default.
- W4387004586 cites W2112796928 @default.
- W4387004586 cites W2131329059 @default.
- W4387004586 cites W2136922672 @default.
- W4387004586 cites W2738226240 @default.
- W4387004586 cites W2808233078 @default.
- W4387004586 cites W2890126432 @default.
- W4387004586 cites W2946794439 @default.
- W4387004586 cites W2963091558 @default.
- W4387004586 cites W2963902947 @default.
- W4387004586 cites W2993548219 @default.
- W4387004586 cites W3087292529 @default.
- W4387004586 cites W3095556171 @default.
- W4387004586 cites W3100014799 @default.
- W4387004586 cites W3115913152 @default.
- W4387004586 cites W3116862438 @default.
- W4387004586 cites W3118199188 @default.
- W4387004586 cites W3140854437 @default.
- W4387004586 cites W3146366485 @default.
- W4387004586 cites W3157594852 @default.
- W4387004586 cites W3159331633 @default.
- W4387004586 cites W3161320446 @default.
- W4387004586 cites W3169602696 @default.
- W4387004586 cites W3177342940 @default.
- W4387004586 cites W3179600265 @default.
- W4387004586 cites W3212945256 @default.
- W4387004586 cites W4214755140 @default.
- W4387004586 cites W4304945145 @default.
- W4387004586 cites W4367301702 @default.
- W4387004586 doi "https://doi.org/10.1016/j.eswa.2023.121734" @default.
- W4387004586 hasPublicationYear "2024" @default.
- W4387004586 type Work @default.
- W4387004586 citedByCount "0" @default.
- W4387004586 crossrefType "journal-article" @default.
- W4387004586 hasAuthorship W4387004586A5014837150 @default.
- W4387004586 hasAuthorship W4387004586A5028046862 @default.
- W4387004586 hasAuthorship W4387004586A5028910864 @default.
- W4387004586 hasAuthorship W4387004586A5029866745 @default.
- W4387004586 hasAuthorship W4387004586A5040048271 @default.
- W4387004586 hasAuthorship W4387004586A5043608851 @default.
- W4387004586 hasAuthorship W4387004586A5084817144 @default.
- W4387004586 hasAuthorship W4387004586A5090330947 @default.
- W4387004586 hasConcept C11413529 @default.
- W4387004586 hasConcept C119857082 @default.
- W4387004586 hasConcept C121332964 @default.
- W4387004586 hasConcept C153180895 @default.
- W4387004586 hasConcept C154945302 @default.
- W4387004586 hasConcept C165801399 @default.
- W4387004586 hasConcept C190502265 @default.
- W4387004586 hasConcept C41008148 @default.
- W4387004586 hasConcept C50644808 @default.
- W4387004586 hasConcept C62520636 @default.
- W4387004586 hasConcept C66322947 @default.
- W4387004586 hasConceptScore W4387004586C11413529 @default.
- W4387004586 hasConceptScore W4387004586C119857082 @default.
- W4387004586 hasConceptScore W4387004586C121332964 @default.
- W4387004586 hasConceptScore W4387004586C153180895 @default.
- W4387004586 hasConceptScore W4387004586C154945302 @default.
- W4387004586 hasConceptScore W4387004586C165801399 @default.
- W4387004586 hasConceptScore W4387004586C190502265 @default.
- W4387004586 hasConceptScore W4387004586C41008148 @default.
- W4387004586 hasConceptScore W4387004586C50644808 @default.
- W4387004586 hasConceptScore W4387004586C62520636 @default.
- W4387004586 hasConceptScore W4387004586C66322947 @default.
- W4387004586 hasLocation W43870045861 @default.
- W4387004586 hasOpenAccess W4387004586 @default.
- W4387004586 hasPrimaryLocation W43870045861 @default.
- W4387004586 hasRelatedWork W2590796488 @default.
- W4387004586 hasRelatedWork W2734358244 @default.
- W4387004586 hasRelatedWork W2750384547 @default.
- W4387004586 hasRelatedWork W2809732489 @default.
- W4387004586 hasRelatedWork W2886711096 @default.
- W4387004586 hasRelatedWork W2950475743 @default.
- W4387004586 hasRelatedWork W3046591097 @default.
- W4387004586 hasRelatedWork W3208266890 @default.
- W4387004586 hasRelatedWork W4380078352 @default.
- W4387004586 hasRelatedWork W4386603768 @default.
- W4387004586 hasVolume "238" @default.
- W4387004586 isParatext "false" @default.
- W4387004586 isRetracted "false" @default.
- W4387004586 workType "article" @default.