Matches in SemOpenAlex for { <https://semopenalex.org/work/W2549252813> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2549252813 abstract "Neural networks are usually over-parameterized with significant redundancy in the number of required neurons which results in unnecessary computation and memory usage at inference time. One common approach to address this issue is to prune these big networks by removing extra neurons and parameters while maintaining the accuracy. In this paper, we propose NoiseOut, a fully automated pruning algorithm based on the correlation between activations of neurons in the hidden layers. We prove that adding additional output neurons with entirely random targets results into a higher correlation between neurons which makes pruning by NoiseOut even more efficient. Finally, we test our method on various networks and datasets. These experiments exhibit high pruning rates while maintaining the accuracy of the original network." @default.
- W2549252813 created "2016-11-30" @default.
- W2549252813 creator A5038903729 @default.
- W2549252813 creator A5049277598 @default.
- W2549252813 creator A5065622216 @default.
- W2549252813 date "2016-11-18" @default.
- W2549252813 modified "2023-09-27" @default.
- W2549252813 title "NoiseOut: A Simple Way to Prune Neural Networks." @default.
- W2549252813 cites W1605708511 @default.
- W2549252813 cites W2004915807 @default.
- W2549252813 cites W2059174629 @default.
- W2549252813 cites W2095705004 @default.
- W2549252813 cites W2112796928 @default.
- W2549252813 cites W2143612262 @default.
- W2549252813 cites W2144629150 @default.
- W2549252813 cites W2194775991 @default.
- W2549252813 cites W2335728318 @default.
- W2549252813 cites W2949560654 @default.
- W2549252813 cites W2950577311 @default.
- W2549252813 hasPublicationYear "2016" @default.
- W2549252813 type Work @default.
- W2549252813 sameAs 2549252813 @default.
- W2549252813 citedByCount "18" @default.
- W2549252813 countsByYear W25492528132017 @default.
- W2549252813 countsByYear W25492528132018 @default.
- W2549252813 countsByYear W25492528132019 @default.
- W2549252813 countsByYear W25492528132020 @default.
- W2549252813 countsByYear W25492528132021 @default.
- W2549252813 crossrefType "posted-content" @default.
- W2549252813 hasAuthorship W2549252813A5038903729 @default.
- W2549252813 hasAuthorship W2549252813A5049277598 @default.
- W2549252813 hasAuthorship W2549252813A5065622216 @default.
- W2549252813 hasConcept C108010975 @default.
- W2549252813 hasConcept C111472728 @default.
- W2549252813 hasConcept C111919701 @default.
- W2549252813 hasConcept C11413529 @default.
- W2549252813 hasConcept C117220453 @default.
- W2549252813 hasConcept C119857082 @default.
- W2549252813 hasConcept C138885662 @default.
- W2549252813 hasConcept C152124472 @default.
- W2549252813 hasConcept C154945302 @default.
- W2549252813 hasConcept C165464430 @default.
- W2549252813 hasConcept C2524010 @default.
- W2549252813 hasConcept C2776214188 @default.
- W2549252813 hasConcept C2780586882 @default.
- W2549252813 hasConcept C2984842247 @default.
- W2549252813 hasConcept C33923547 @default.
- W2549252813 hasConcept C41008148 @default.
- W2549252813 hasConcept C45374587 @default.
- W2549252813 hasConcept C50644808 @default.
- W2549252813 hasConcept C6557445 @default.
- W2549252813 hasConcept C86803240 @default.
- W2549252813 hasConceptScore W2549252813C108010975 @default.
- W2549252813 hasConceptScore W2549252813C111472728 @default.
- W2549252813 hasConceptScore W2549252813C111919701 @default.
- W2549252813 hasConceptScore W2549252813C11413529 @default.
- W2549252813 hasConceptScore W2549252813C117220453 @default.
- W2549252813 hasConceptScore W2549252813C119857082 @default.
- W2549252813 hasConceptScore W2549252813C138885662 @default.
- W2549252813 hasConceptScore W2549252813C152124472 @default.
- W2549252813 hasConceptScore W2549252813C154945302 @default.
- W2549252813 hasConceptScore W2549252813C165464430 @default.
- W2549252813 hasConceptScore W2549252813C2524010 @default.
- W2549252813 hasConceptScore W2549252813C2776214188 @default.
- W2549252813 hasConceptScore W2549252813C2780586882 @default.
- W2549252813 hasConceptScore W2549252813C2984842247 @default.
- W2549252813 hasConceptScore W2549252813C33923547 @default.
- W2549252813 hasConceptScore W2549252813C41008148 @default.
- W2549252813 hasConceptScore W2549252813C45374587 @default.
- W2549252813 hasConceptScore W2549252813C50644808 @default.
- W2549252813 hasConceptScore W2549252813C6557445 @default.
- W2549252813 hasConceptScore W2549252813C86803240 @default.
- W2549252813 hasLocation W25492528131 @default.
- W2549252813 hasOpenAccess W2549252813 @default.
- W2549252813 hasPrimaryLocation W25492528131 @default.
- W2549252813 hasRelatedWork W2095705004 @default.
- W2549252813 hasRelatedWork W2114766824 @default.
- W2549252813 hasRelatedWork W2125389748 @default.
- W2549252813 hasRelatedWork W2194775991 @default.
- W2549252813 hasRelatedWork W2495425901 @default.
- W2549252813 hasRelatedWork W2540366045 @default.
- W2549252813 hasRelatedWork W2605229985 @default.
- W2549252813 hasRelatedWork W2751981785 @default.
- W2549252813 hasRelatedWork W2952423590 @default.
- W2549252813 hasRelatedWork W2963145730 @default.
- W2549252813 hasRelatedWork W2963674932 @default.
- W2549252813 hasRelatedWork W2964217848 @default.
- W2549252813 hasRelatedWork W2964299589 @default.
- W2549252813 hasRelatedWork W2996577930 @default.
- W2549252813 hasRelatedWork W3009616221 @default.
- W2549252813 hasRelatedWork W3023585672 @default.
- W2549252813 hasRelatedWork W3048959830 @default.
- W2549252813 hasRelatedWork W3118608800 @default.
- W2549252813 hasRelatedWork W3162274736 @default.
- W2549252813 hasRelatedWork W3206105267 @default.
- W2549252813 isParatext "false" @default.
- W2549252813 isRetracted "false" @default.
- W2549252813 magId "2549252813" @default.
- W2549252813 workType "article" @default.