Matches in SemOpenAlex for { <https://semopenalex.org/work/W2250904038> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2250904038 abstract "There has been a recent surge of success in utilizing Deep Learning (DL) in imaging and speech applications for its relatively automatic feature generation and, in particular for convolutional neural networks (CNNs), high accuracy classification abilities. While these models learn their parameters through data-driven methods, model selection (as architecture construction) through hyper-parameter choices remains a tedious and highly intuition driven task. To address this, Multi-node Evolutionary Neural Networks for Deep Learning (MENNDL) is proposed as a method for automating network selection on computational clusters through hyper-parameter optimization performed via genetic algorithms." @default.
- W2250904038 created "2016-06-24" @default.
- W2250904038 creator A5004617550 @default.
- W2250904038 creator A5021986280 @default.
- W2250904038 creator A5029444976 @default.
- W2250904038 creator A5029824262 @default.
- W2250904038 creator A5070858681 @default.
- W2250904038 date "2015-11-15" @default.
- W2250904038 modified "2023-10-18" @default.
- W2250904038 title "Optimizing deep learning hyper-parameters through an evolutionary algorithm" @default.
- W2250904038 cites W1617447347 @default.
- W2250904038 cites W1677182931 @default.
- W2250904038 cites W1976981886 @default.
- W2250904038 cites W2125621954 @default.
- W2250904038 cites W2155893237 @default.
- W2250904038 cites W2160815625 @default.
- W2250904038 cites W2165132362 @default.
- W2250904038 cites W276602078 @default.
- W2250904038 doi "https://doi.org/10.1145/2834892.2834896" @default.
- W2250904038 hasPublicationYear "2015" @default.
- W2250904038 type Work @default.
- W2250904038 sameAs 2250904038 @default.
- W2250904038 citedByCount "231" @default.
- W2250904038 countsByYear W22509040382016 @default.
- W2250904038 countsByYear W22509040382017 @default.
- W2250904038 countsByYear W22509040382018 @default.
- W2250904038 countsByYear W22509040382019 @default.
- W2250904038 countsByYear W22509040382020 @default.
- W2250904038 countsByYear W22509040382021 @default.
- W2250904038 countsByYear W22509040382022 @default.
- W2250904038 countsByYear W22509040382023 @default.
- W2250904038 crossrefType "proceedings-article" @default.
- W2250904038 hasAuthorship W2250904038A5004617550 @default.
- W2250904038 hasAuthorship W2250904038A5021986280 @default.
- W2250904038 hasAuthorship W2250904038A5029444976 @default.
- W2250904038 hasAuthorship W2250904038A5029824262 @default.
- W2250904038 hasAuthorship W2250904038A5070858681 @default.
- W2250904038 hasConcept C105902424 @default.
- W2250904038 hasConcept C108583219 @default.
- W2250904038 hasConcept C111472728 @default.
- W2250904038 hasConcept C119857082 @default.
- W2250904038 hasConcept C132010649 @default.
- W2250904038 hasConcept C138885662 @default.
- W2250904038 hasConcept C154945302 @default.
- W2250904038 hasConcept C159149176 @default.
- W2250904038 hasConcept C2984842247 @default.
- W2250904038 hasConcept C41008148 @default.
- W2250904038 hasConcept C50644808 @default.
- W2250904038 hasConcept C81363708 @default.
- W2250904038 hasConcept C81917197 @default.
- W2250904038 hasConceptScore W2250904038C105902424 @default.
- W2250904038 hasConceptScore W2250904038C108583219 @default.
- W2250904038 hasConceptScore W2250904038C111472728 @default.
- W2250904038 hasConceptScore W2250904038C119857082 @default.
- W2250904038 hasConceptScore W2250904038C132010649 @default.
- W2250904038 hasConceptScore W2250904038C138885662 @default.
- W2250904038 hasConceptScore W2250904038C154945302 @default.
- W2250904038 hasConceptScore W2250904038C159149176 @default.
- W2250904038 hasConceptScore W2250904038C2984842247 @default.
- W2250904038 hasConceptScore W2250904038C41008148 @default.
- W2250904038 hasConceptScore W2250904038C50644808 @default.
- W2250904038 hasConceptScore W2250904038C81363708 @default.
- W2250904038 hasConceptScore W2250904038C81917197 @default.
- W2250904038 hasLocation W22509040381 @default.
- W2250904038 hasOpenAccess W2250904038 @default.
- W2250904038 hasPrimaryLocation W22509040381 @default.
- W2250904038 hasRelatedWork W2535731875 @default.
- W2250904038 hasRelatedWork W2922457425 @default.
- W2250904038 hasRelatedWork W3124051732 @default.
- W2250904038 hasRelatedWork W3215138031 @default.
- W2250904038 hasRelatedWork W4223943233 @default.
- W2250904038 hasRelatedWork W4225161397 @default.
- W2250904038 hasRelatedWork W4229568052 @default.
- W2250904038 hasRelatedWork W4237634094 @default.
- W2250904038 hasRelatedWork W4247102092 @default.
- W2250904038 hasRelatedWork W4250304930 @default.
- W2250904038 isParatext "false" @default.
- W2250904038 isRetracted "false" @default.
- W2250904038 magId "2250904038" @default.
- W2250904038 workType "article" @default.