Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377971424> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4377971424 endingPage "15" @default.
- W4377971424 startingPage "1" @default.
- W4377971424 abstract "Neural architecture search (NAS) has recently gained extensive interest in the deep learning community because of its great potential in automating the construction process of deep models. Among a variety of NAS approaches, evolutionary computation (EC) plays a pivotal role with its merit of gradient-free search ability. However, a massive number of the current EC-based NAS approaches evolve neural architectures in an absolutely discrete manner, which makes it tough to flexibly handle the number of filters for each layer, since they often reduce it to a limit set rather than searching for all possible values. Moreover, EC-based NAS methods are often criticized for their inefficiency in performance evaluation, which usually requires laborious full training for hundreds of candidate architectures generated. To address the inflexible search issue on the number of filters, this work proposes a split-level particle swarm optimization (PSO) approach. Each dimension of the particle is subdivided into an integer part and a fractional part, encoding the configurations of the corresponding layer, and the number of filters within a large range, respectively. In addition, the evaluation time is greatly saved by a novel elite weight inheritance method based on an online updating weight pool, and a customized fitness function considering multiple objectives is developed to well control the complexity of the searched candidate architectures. The proposed method, termed split-level evolutionary NAS (SLE-NAS), is computationally efficient, and outperforms many state-of-the-art peer competitors at much lower complexity across three popular image classification benchmark datasets." @default.
- W4377971424 created "2023-05-25" @default.
- W4377971424 creator A5010638666 @default.
- W4377971424 creator A5016371456 @default.
- W4377971424 creator A5025522422 @default.
- W4377971424 creator A5077569089 @default.
- W4377971424 creator A5091058342 @default.
- W4377971424 date "2023-01-01" @default.
- W4377971424 modified "2023-09-28" @default.
- W4377971424 title "Split-Level Evolutionary Neural Architecture Search With Elite Weight Inheritance" @default.
- W4377971424 doi "https://doi.org/10.1109/tnnls.2023.3269816" @default.
- W4377971424 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37224355" @default.
- W4377971424 hasPublicationYear "2023" @default.
- W4377971424 type Work @default.
- W4377971424 citedByCount "0" @default.
- W4377971424 crossrefType "journal-article" @default.
- W4377971424 hasAuthorship W4377971424A5010638666 @default.
- W4377971424 hasAuthorship W4377971424A5016371456 @default.
- W4377971424 hasAuthorship W4377971424A5025522422 @default.
- W4377971424 hasAuthorship W4377971424A5077569089 @default.
- W4377971424 hasAuthorship W4377971424A5091058342 @default.
- W4377971424 hasConcept C104317684 @default.
- W4377971424 hasConcept C105902424 @default.
- W4377971424 hasConcept C119857082 @default.
- W4377971424 hasConcept C127413603 @default.
- W4377971424 hasConcept C13280743 @default.
- W4377971424 hasConcept C146978453 @default.
- W4377971424 hasConcept C154945302 @default.
- W4377971424 hasConcept C159149176 @default.
- W4377971424 hasConcept C176066374 @default.
- W4377971424 hasConcept C177264268 @default.
- W4377971424 hasConcept C185592680 @default.
- W4377971424 hasConcept C185798385 @default.
- W4377971424 hasConcept C199360897 @default.
- W4377971424 hasConcept C204323151 @default.
- W4377971424 hasConcept C205649164 @default.
- W4377971424 hasConcept C2780902518 @default.
- W4377971424 hasConcept C41008148 @default.
- W4377971424 hasConcept C50644808 @default.
- W4377971424 hasConcept C55493867 @default.
- W4377971424 hasConcept C85617194 @default.
- W4377971424 hasConcept C8880873 @default.
- W4377971424 hasConceptScore W4377971424C104317684 @default.
- W4377971424 hasConceptScore W4377971424C105902424 @default.
- W4377971424 hasConceptScore W4377971424C119857082 @default.
- W4377971424 hasConceptScore W4377971424C127413603 @default.
- W4377971424 hasConceptScore W4377971424C13280743 @default.
- W4377971424 hasConceptScore W4377971424C146978453 @default.
- W4377971424 hasConceptScore W4377971424C154945302 @default.
- W4377971424 hasConceptScore W4377971424C159149176 @default.
- W4377971424 hasConceptScore W4377971424C176066374 @default.
- W4377971424 hasConceptScore W4377971424C177264268 @default.
- W4377971424 hasConceptScore W4377971424C185592680 @default.
- W4377971424 hasConceptScore W4377971424C185798385 @default.
- W4377971424 hasConceptScore W4377971424C199360897 @default.
- W4377971424 hasConceptScore W4377971424C204323151 @default.
- W4377971424 hasConceptScore W4377971424C205649164 @default.
- W4377971424 hasConceptScore W4377971424C2780902518 @default.
- W4377971424 hasConceptScore W4377971424C41008148 @default.
- W4377971424 hasConceptScore W4377971424C50644808 @default.
- W4377971424 hasConceptScore W4377971424C55493867 @default.
- W4377971424 hasConceptScore W4377971424C85617194 @default.
- W4377971424 hasConceptScore W4377971424C8880873 @default.
- W4377971424 hasFunder F4320321001 @default.
- W4377971424 hasLocation W43779714241 @default.
- W4377971424 hasLocation W43779714242 @default.
- W4377971424 hasOpenAccess W4377971424 @default.
- W4377971424 hasPrimaryLocation W43779714241 @default.
- W4377971424 hasRelatedWork W1986958725 @default.
- W4377971424 hasRelatedWork W2072268707 @default.
- W4377971424 hasRelatedWork W2074959697 @default.
- W4377971424 hasRelatedWork W2362646746 @default.
- W4377971424 hasRelatedWork W2371761421 @default.
- W4377971424 hasRelatedWork W3194144547 @default.
- W4377971424 hasRelatedWork W4229568052 @default.
- W4377971424 hasRelatedWork W4288388966 @default.
- W4377971424 hasRelatedWork W1598981949 @default.
- W4377971424 hasRelatedWork W1842957617 @default.
- W4377971424 isParatext "false" @default.
- W4377971424 isRetracted "false" @default.
- W4377971424 workType "article" @default.