FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176543706> ?p ?o ?g. }

• W3176543706 endingPage "1084" @default.
• W3176543706 startingPage "1070" @default.
• W3176543706 abstract "Abstract State-of-the-art deep neural network plays an increasingly important role in artificial intelligence, while the huge number of parameters in networks brings high memory cost and computational complexity. To solve this problem, filter pruning is widely used for neural network compression and acceleration. However, existing algorithms focus mainly on pruning single model, and few results are available to multi-task pruning that is capable of pruning multi-model and promoting the learning performance. By utilizing the filter sharing technique, this paper aimed to establish a multi-task pruning framework for simultaneously pruning and merging filters in multi-task networks. An optimization problem of selecting the important filters is solved by developing a many-objective optimization algorithm where three criteria are adopted as objectives for the many-objective optimization problem. With the purpose of keeping the network structure, an index matrix is introduced to regulate the information sharing during multi-task training. The proposed multi-task pruning algorithm is quite flexible that can be performed with either adaptive or pre-specified pruning rates. Extensive experiments are performed to verify the applicability and superiority of the proposed method on both single-task and multi-task pruning." @default.
• W3176543706 created "2021-07-05" @default.
• W3176543706 creator A5010455773 @default.
• W3176543706 creator A5035358476 @default.
• W3176543706 creator A5048831651 @default.
• W3176543706 creator A5067275668 @default.
• W3176543706 creator A5070343691 @default.
• W3176543706 date "2021-06-25" @default.
• W3176543706 modified "2023-10-17" @default.
• W3176543706 title "Multi-task Pruning via Filter Index Sharing: A Many-Objective Optimization Approach" @default.
• W3176543706 cites W2112796928 @default.
• W3176543706 cites W2117539524 @default.
• W3176543706 cites W2143381319 @default.
• W3176543706 cites W2194775991 @default.
• W3176543706 cites W2473930607 @default.
• W3176543706 cites W2519119178 @default.
• W3176543706 cites W2549401308 @default.
• W3176543706 cites W2604998962 @default.
• W3176543706 cites W2798603777 @default.
• W3176543706 cites W2808168148 @default.
• W3176543706 cites W2891943454 @default.
• W3176543706 cites W2894895904 @default.
• W3176543706 cites W2907039237 @default.
• W3176543706 cites W2908142178 @default.
• W3176543706 cites W2918988263 @default.
• W3176543706 cites W2928560789 @default.
• W3176543706 cites W2963145730 @default.
• W3176543706 cites W2963363373 @default.
• W3176543706 cites W2963377935 @default.
• W3176543706 cites W2963877604 @default.
• W3176543706 cites W2964233199 @default.
• W3176543706 cites W2970958999 @default.
• W3176543706 cites W2984618279 @default.
• W3176543706 cites W2996540419 @default.
• W3176543706 cites W2996649902 @default.
• W3176543706 cites W3000341120 @default.
• W3176543706 cites W3001028887 @default.
• W3176543706 cites W3007062453 @default.
• W3176543706 cites W3034235489 @default.
• W3176543706 cites W3034251466 @default.
• W3176543706 cites W3034513523 @default.
• W3176543706 cites W3043165038 @default.
• W3176543706 cites W3044539706 @default.
• W3176543706 cites W3045184377 @default.
• W3176543706 cites W3046310786 @default.
• W3176543706 cites W3049654296 @default.
• W3176543706 cites W3049686946 @default.
• W3176543706 cites W3082334751 @default.
• W3176543706 cites W3084378749 @default.
• W3176543706 cites W3097484241 @default.
• W3176543706 cites W3111817041 @default.
• W3176543706 cites W3166033322 @default.
• W3176543706 doi "https://doi.org/10.1007/s12559-021-09894-x" @default.
• W3176543706 hasPublicationYear "2021" @default.
• W3176543706 type Work @default.
• W3176543706 sameAs 3176543706 @default.
• W3176543706 citedByCount "7" @default.
• W3176543706 countsByYear W31765437062022 @default.
• W3176543706 countsByYear W31765437062023 @default.
• W3176543706 crossrefType "journal-article" @default.
• W3176543706 hasAuthorship W3176543706A5010455773 @default.
• W3176543706 hasAuthorship W3176543706A5035358476 @default.
• W3176543706 hasAuthorship W3176543706A5048831651 @default.
• W3176543706 hasAuthorship W3176543706A5067275668 @default.
• W3176543706 hasAuthorship W3176543706A5070343691 @default.
• W3176543706 hasBestOaLocation W31765437061 @default.
• W3176543706 hasConcept C106131492 @default.
• W3176543706 hasConcept C108010975 @default.
• W3176543706 hasConcept C119857082 @default.
• W3176543706 hasConcept C154945302 @default.
• W3176543706 hasConcept C162324750 @default.
• W3176543706 hasConcept C187736073 @default.
• W3176543706 hasConcept C2780451532 @default.
• W3176543706 hasConcept C31972630 @default.
• W3176543706 hasConcept C41008148 @default.
• W3176543706 hasConcept C50644808 @default.
• W3176543706 hasConcept C6557445 @default.
• W3176543706 hasConcept C86803240 @default.
• W3176543706 hasConceptScore W3176543706C106131492 @default.
• W3176543706 hasConceptScore W3176543706C108010975 @default.
• W3176543706 hasConceptScore W3176543706C119857082 @default.
• W3176543706 hasConceptScore W3176543706C154945302 @default.
• W3176543706 hasConceptScore W3176543706C162324750 @default.
• W3176543706 hasConceptScore W3176543706C187736073 @default.
• W3176543706 hasConceptScore W3176543706C2780451532 @default.
• W3176543706 hasConceptScore W3176543706C31972630 @default.
• W3176543706 hasConceptScore W3176543706C41008148 @default.
• W3176543706 hasConceptScore W3176543706C50644808 @default.
• W3176543706 hasConceptScore W3176543706C6557445 @default.
• W3176543706 hasConceptScore W3176543706C86803240 @default.
• W3176543706 hasIssue "4" @default.
• W3176543706 hasLocation W31765437061 @default.
• W3176543706 hasLocation W31765437062 @default.
• W3176543706 hasOpenAccess W3176543706 @default.
• W3176543706 hasPrimaryLocation W31765437061 @default.
• W3176543706 hasRelatedWork W1879310460 @default.
• W3176543706 hasRelatedWork W2899084033 @default.
• W3176543706 hasRelatedWork W2961085424 @default.

• next