Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285264465> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4285264465 endingPage "155" @default.
- W4285264465 startingPage "143" @default.
- W4285264465 abstract "Time series classification (TSC) aims to assign labels to time series. Deep learning methods, such as InceptionTime and Transformer, achieve promising performances in TSC. Although deep learning methods do not require manually crafted features, they do require careful manual design of the network structure. The design of architectures heavily relies on researchers’ prior knowledge and experience. Due to the limitations of human’s knowledge, the designed architecture may not be optimal on the dataset of interest. To automate and optimize the architecture design, we propose a data-driven TSC network architecture design method called AutoTransformer. AutoTransformer designs the suitable network architecture automatically depending on the target TSC dataset. Inspired by the overall architecture of Transformer, we first propose a novel search space tailored for TSC. The search space includes a variety of substructures that are capable of extracting global and local features from time series. Then, with the help of neural architecture search (NAS) technique, a suitable network architecture for the target TSC dataset can be found from the search space. Experimental results show that AutoTransformer finds proper architectures on different TSC datasets and outperforms state-of-the-art methods on the UCR archive. Ablation studies verify the effectiveness of the proposed search space." @default.
- W4285264465 created "2022-07-14" @default.
- W4285264465 creator A5001741551 @default.
- W4285264465 creator A5030671408 @default.
- W4285264465 creator A5045140292 @default.
- W4285264465 creator A5084848859 @default.
- W4285264465 date "2022-01-01" @default.
- W4285264465 modified "2023-09-25" @default.
- W4285264465 title "AutoTransformer: Automatic Transformer Architecture Design for Time Series Classification" @default.
- W4285264465 cites W1903029394 @default.
- W4285264465 cites W1968354112 @default.
- W4285264465 cites W1975257359 @default.
- W4285264465 cites W1984674851 @default.
- W4285264465 cites W2029438113 @default.
- W4285264465 cites W2050493487 @default.
- W4285264465 cites W2064675550 @default.
- W4285264465 cites W2081028405 @default.
- W4285264465 cites W2166547175 @default.
- W4285264465 cites W2194775991 @default.
- W4285264465 cites W2551393996 @default.
- W4285264465 cites W2555077524 @default.
- W4285264465 cites W2754051771 @default.
- W4285264465 cites W2786161686 @default.
- W4285264465 cites W2892035503 @default.
- W4285264465 cites W2960010704 @default.
- W4285264465 cites W2964081807 @default.
- W4285264465 cites W3010158807 @default.
- W4285264465 cites W3034309359 @default.
- W4285264465 cites W3042807565 @default.
- W4285264465 cites W848133049 @default.
- W4285264465 doi "https://doi.org/10.1007/978-3-031-05933-9_12" @default.
- W4285264465 hasPublicationYear "2022" @default.
- W4285264465 type Work @default.
- W4285264465 citedByCount "1" @default.
- W4285264465 countsByYear W42852644652023 @default.
- W4285264465 crossrefType "book-chapter" @default.
- W4285264465 hasAuthorship W4285264465A5001741551 @default.
- W4285264465 hasAuthorship W4285264465A5030671408 @default.
- W4285264465 hasAuthorship W4285264465A5045140292 @default.
- W4285264465 hasAuthorship W4285264465A5084848859 @default.
- W4285264465 hasConcept C108583219 @default.
- W4285264465 hasConcept C117323899 @default.
- W4285264465 hasConcept C119599485 @default.
- W4285264465 hasConcept C119857082 @default.
- W4285264465 hasConcept C123657996 @default.
- W4285264465 hasConcept C124101348 @default.
- W4285264465 hasConcept C127413603 @default.
- W4285264465 hasConcept C142362112 @default.
- W4285264465 hasConcept C153349607 @default.
- W4285264465 hasConcept C154945302 @default.
- W4285264465 hasConcept C165801399 @default.
- W4285264465 hasConcept C193415008 @default.
- W4285264465 hasConcept C22958824 @default.
- W4285264465 hasConcept C38652104 @default.
- W4285264465 hasConcept C41008148 @default.
- W4285264465 hasConcept C50644808 @default.
- W4285264465 hasConcept C66322947 @default.
- W4285264465 hasConceptScore W4285264465C108583219 @default.
- W4285264465 hasConceptScore W4285264465C117323899 @default.
- W4285264465 hasConceptScore W4285264465C119599485 @default.
- W4285264465 hasConceptScore W4285264465C119857082 @default.
- W4285264465 hasConceptScore W4285264465C123657996 @default.
- W4285264465 hasConceptScore W4285264465C124101348 @default.
- W4285264465 hasConceptScore W4285264465C127413603 @default.
- W4285264465 hasConceptScore W4285264465C142362112 @default.
- W4285264465 hasConceptScore W4285264465C153349607 @default.
- W4285264465 hasConceptScore W4285264465C154945302 @default.
- W4285264465 hasConceptScore W4285264465C165801399 @default.
- W4285264465 hasConceptScore W4285264465C193415008 @default.
- W4285264465 hasConceptScore W4285264465C22958824 @default.
- W4285264465 hasConceptScore W4285264465C38652104 @default.
- W4285264465 hasConceptScore W4285264465C41008148 @default.
- W4285264465 hasConceptScore W4285264465C50644808 @default.
- W4285264465 hasConceptScore W4285264465C66322947 @default.
- W4285264465 hasLocation W42852644651 @default.
- W4285264465 hasOpenAccess W4285264465 @default.
- W4285264465 hasPrimaryLocation W42852644651 @default.
- W4285264465 hasRelatedWork W3014300295 @default.
- W4285264465 hasRelatedWork W3164822677 @default.
- W4285264465 hasRelatedWork W4223943233 @default.
- W4285264465 hasRelatedWork W4225161397 @default.
- W4285264465 hasRelatedWork W4309045103 @default.
- W4285264465 hasRelatedWork W4312200629 @default.
- W4285264465 hasRelatedWork W4360585206 @default.
- W4285264465 hasRelatedWork W4364306694 @default.
- W4285264465 hasRelatedWork W4380075502 @default.
- W4285264465 hasRelatedWork W4380086463 @default.
- W4285264465 isParatext "false" @default.
- W4285264465 isRetracted "false" @default.
- W4285264465 workType "book-chapter" @default.