Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897792138> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2897792138 endingPage "60444" @default.
- W2897792138 startingPage "60438" @default.
- W2897792138 abstract "This paper presents a study on the applicability of using approximate multipliers to enhance the performance of the VGGNet deep learning network. Approximate multipliers are known to have reduced power, area, and delay with the cost of an inaccuracy in output. Improving the performance of the VGGNet in terms of power, area, and speed can be achieved by replacing exact multipliers with approximate multipliers as demonstrated in this paper. The simulation results show that approximate multiplication has a very little impact on the accuracy of VGGNet. However, using approximate multipliers can achieve significant performance gains. The simulation was completed using different generated error matrices that mimic the inaccuracy that approximate multipliers introduce to the data. The impact of various ranges of the mean relative error and the standard deviation was tested. The well-known data sets CIFAR-10 and CIFAR100 were used for testing the network's classification accuracy. The impact on the accuracy was assessed by simulating approximate multiplication in all the layers in the first set of tests, and in selective layers in the second set of tests. Using approximate multipliers in all the layers leads to very little impact on the network's accuracy. In addition, an alternative approach is to use a hybrid of exact and approximate multipliers. In the hybrid approach, 39.14% of the deeper layer's multiplications can be approximate while having a reduced negligible impact on the network's accuracy." @default.
- W2897792138 created "2018-10-26" @default.
- W2897792138 creator A5076483141 @default.
- W2897792138 creator A5089770187 @default.
- W2897792138 date "2018-01-01" @default.
- W2897792138 modified "2023-10-01" @default.
- W2897792138 title "Impact of Approximate Multipliers on VGG Deep Learning Network" @default.
- W2897792138 cites W2323130283 @default.
- W2897792138 cites W2417429787 @default.
- W2897792138 cites W2533121491 @default.
- W2897792138 cites W2578985517 @default.
- W2897792138 cites W2604319603 @default.
- W2897792138 cites W2734572653 @default.
- W2897792138 cites W2769672439 @default.
- W2897792138 cites W2770978880 @default.
- W2897792138 cites W3116537075 @default.
- W2897792138 cites W4249697915 @default.
- W2897792138 cites W4362215237 @default.
- W2897792138 doi "https://doi.org/10.1109/access.2018.2875376" @default.
- W2897792138 hasPublicationYear "2018" @default.
- W2897792138 type Work @default.
- W2897792138 sameAs 2897792138 @default.
- W2897792138 citedByCount "38" @default.
- W2897792138 countsByYear W28977921382019 @default.
- W2897792138 countsByYear W28977921382020 @default.
- W2897792138 countsByYear W28977921382021 @default.
- W2897792138 countsByYear W28977921382022 @default.
- W2897792138 countsByYear W28977921382023 @default.
- W2897792138 crossrefType "journal-article" @default.
- W2897792138 hasAuthorship W2897792138A5076483141 @default.
- W2897792138 hasAuthorship W2897792138A5089770187 @default.
- W2897792138 hasBestOaLocation W28977921381 @default.
- W2897792138 hasConcept C11413529 @default.
- W2897792138 hasConcept C114614502 @default.
- W2897792138 hasConcept C122383733 @default.
- W2897792138 hasConcept C126255220 @default.
- W2897792138 hasConcept C177264268 @default.
- W2897792138 hasConcept C199360897 @default.
- W2897792138 hasConcept C2780595030 @default.
- W2897792138 hasConcept C33923547 @default.
- W2897792138 hasConcept C41008148 @default.
- W2897792138 hasConceptScore W2897792138C11413529 @default.
- W2897792138 hasConceptScore W2897792138C114614502 @default.
- W2897792138 hasConceptScore W2897792138C122383733 @default.
- W2897792138 hasConceptScore W2897792138C126255220 @default.
- W2897792138 hasConceptScore W2897792138C177264268 @default.
- W2897792138 hasConceptScore W2897792138C199360897 @default.
- W2897792138 hasConceptScore W2897792138C2780595030 @default.
- W2897792138 hasConceptScore W2897792138C33923547 @default.
- W2897792138 hasConceptScore W2897792138C41008148 @default.
- W2897792138 hasLocation W28977921381 @default.
- W2897792138 hasOpenAccess W2897792138 @default.
- W2897792138 hasPrimaryLocation W28977921381 @default.
- W2897792138 hasRelatedWork W2025258469 @default.
- W2897792138 hasRelatedWork W2040345527 @default.
- W2897792138 hasRelatedWork W2114616060 @default.
- W2897792138 hasRelatedWork W2142381314 @default.
- W2897792138 hasRelatedWork W2168631902 @default.
- W2897792138 hasRelatedWork W2189559640 @default.
- W2897792138 hasRelatedWork W2355215981 @default.
- W2897792138 hasRelatedWork W2386767533 @default.
- W2897792138 hasRelatedWork W2511377649 @default.
- W2897792138 hasRelatedWork W848451299 @default.
- W2897792138 hasVolume "6" @default.
- W2897792138 isParatext "false" @default.
- W2897792138 isRetracted "false" @default.
- W2897792138 magId "2897792138" @default.
- W2897792138 workType "article" @default.