Matches in SemOpenAlex for { <https://semopenalex.org/work/W2959643294> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2959643294 abstract "In recent decades, deep learning approaches have shown impressive results in many applications. However, most of these approaches rely on manually crafted architectures for a specific task in large design space, allowing room for sub-optimal designs, which are more prone to be stuck in local minima and to overfit. Therefore, there is considerable motivation in performing architecture search for solving a specific task. In this work, we propose an initialization technique for design space exploration of deep neural networks architectures based on Latin Hypercube Sampling (LHS). When compared with random initialization using standard datasets in machine learning such as MNIST, and CIFAR-10, the proposed approach shows to be promissory on the neural architectural search domain, outperforming the commonly used random initialization." @default.
- W2959643294 created "2019-07-23" @default.
- W2959643294 creator A5044936138 @default.
- W2959643294 creator A5049319582 @default.
- W2959643294 creator A5059245199 @default.
- W2959643294 creator A5063080704 @default.
- W2959643294 date "2019-07-13" @default.
- W2959643294 modified "2023-09-23" @default.
- W2959643294 title "Latin hypercube initialization strategy for design space exploration of deep neural network architectures" @default.
- W2959643294 cites W2038669746 @default.
- W2959643294 cites W2068696225 @default.
- W2959643294 cites W2112796928 @default.
- W2959643294 doi "https://doi.org/10.1145/3319619.3321922" @default.
- W2959643294 hasPublicationYear "2019" @default.
- W2959643294 type Work @default.
- W2959643294 sameAs 2959643294 @default.
- W2959643294 citedByCount "2" @default.
- W2959643294 countsByYear W29596432942022 @default.
- W2959643294 countsByYear W29596432942023 @default.
- W2959643294 crossrefType "proceedings-article" @default.
- W2959643294 hasAuthorship W2959643294A5044936138 @default.
- W2959643294 hasAuthorship W2959643294A5049319582 @default.
- W2959643294 hasAuthorship W2959643294A5059245199 @default.
- W2959643294 hasAuthorship W2959643294A5063080704 @default.
- W2959643294 hasConcept C105795698 @default.
- W2959643294 hasConcept C111919701 @default.
- W2959643294 hasConcept C114466953 @default.
- W2959643294 hasConcept C154945302 @default.
- W2959643294 hasConcept C173608175 @default.
- W2959643294 hasConcept C19499675 @default.
- W2959643294 hasConcept C199360897 @default.
- W2959643294 hasConcept C20820323 @default.
- W2959643294 hasConcept C2778572836 @default.
- W2959643294 hasConcept C2984842247 @default.
- W2959643294 hasConcept C33923547 @default.
- W2959643294 hasConcept C41008148 @default.
- W2959643294 hasConcept C50644808 @default.
- W2959643294 hasConcept C50820777 @default.
- W2959643294 hasConceptScore W2959643294C105795698 @default.
- W2959643294 hasConceptScore W2959643294C111919701 @default.
- W2959643294 hasConceptScore W2959643294C114466953 @default.
- W2959643294 hasConceptScore W2959643294C154945302 @default.
- W2959643294 hasConceptScore W2959643294C173608175 @default.
- W2959643294 hasConceptScore W2959643294C19499675 @default.
- W2959643294 hasConceptScore W2959643294C199360897 @default.
- W2959643294 hasConceptScore W2959643294C20820323 @default.
- W2959643294 hasConceptScore W2959643294C2778572836 @default.
- W2959643294 hasConceptScore W2959643294C2984842247 @default.
- W2959643294 hasConceptScore W2959643294C33923547 @default.
- W2959643294 hasConceptScore W2959643294C41008148 @default.
- W2959643294 hasConceptScore W2959643294C50644808 @default.
- W2959643294 hasConceptScore W2959643294C50820777 @default.
- W2959643294 hasLocation W29596432941 @default.
- W2959643294 hasOpenAccess W2959643294 @default.
- W2959643294 hasPrimaryLocation W29596432941 @default.
- W2959643294 hasRelatedWork W1766800773 @default.
- W2959643294 hasRelatedWork W2558621277 @default.
- W2959643294 hasRelatedWork W2765525762 @default.
- W2959643294 hasRelatedWork W2955304652 @default.
- W2959643294 hasRelatedWork W2975160087 @default.
- W2959643294 hasRelatedWork W2986558930 @default.
- W2959643294 hasRelatedWork W4210425613 @default.
- W2959643294 hasRelatedWork W4226225164 @default.
- W2959643294 hasRelatedWork W4295006205 @default.
- W2959643294 hasRelatedWork W2118665868 @default.
- W2959643294 isParatext "false" @default.
- W2959643294 isRetracted "false" @default.
- W2959643294 magId "2959643294" @default.
- W2959643294 workType "article" @default.