FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224234949> ?p ?o ?g. }

• W4224234949 endingPage "1178" @default.
• W4224234949 startingPage "1178" @default.
• W4224234949 abstract "This study presents a universal reconfigurable hardware accelerator for efficient processing of sparse decision trees, artificial neural networks and support vector machines. The main idea is to develop a hardware accelerator that will be able to directly process sparse machine learning models, resulting in shorter inference times and lower power consumption compared to existing solutions. To the author’s best knowledge, this is the first hardware accelerator of this type. Additionally, this is the first accelerator that is capable of processing sparse machine learning models of different types. Besides the hardware accelerator itself, algorithms for induction of sparse decision trees, pruning of support vector machines and artificial neural networks are presented. Such sparse machine learning classifiers are attractive since they require significantly less memory resources for storing model parameters. This results in reduced data movement between the accelerator and the DRAM memory, as well as a reduced number of operations required to process input instances, leading to faster and more energy-efficient processing. This could be of a significant interest in edge-based applications, with severely constrained memory, computation resources and power consumption. The performance of algorithms and the developed hardware accelerator are demonstrated using standard benchmark datasets from the UCI Machine Learning Repository database. The results of the experimental study reveal that the proposed algorithms and presented hardware accelerator are superior when compared to some of the existing solutions. Throughput is increased up to 2 times for decision trees, 2.3 times for support vector machines and 38 times for artificial neural networks. When the processing latency is considered, maximum performance improvement is even higher: up to a 4.4 times reduction for decision trees, a 84.1 times reduction for support vector machines and a 22.2 times reduction for artificial neural networks. Finally, since it is capable of supporting sparse classifiers, the usage of the proposed hardware accelerator leads to a significant reduction in energy spent on DRAM data transfers and a reduction of 50.16% for decision trees, 93.65% for support vector machines and as much as 93.75% for artificial neural networks, respectively." @default.
• W4224234949 created "2022-04-26" @default.
• W4224234949 creator A5065879404 @default.
• W4224234949 creator A5066612315 @default.
• W4224234949 creator A5080935074 @default.
• W4224234949 date "2022-04-08" @default.
• W4224234949 modified "2023-10-14" @default.
• W4224234949 title "Universal Reconfigurable Hardware Accelerator for Sparse Machine Learning Predictive Models" @default.
• W4224234949 cites W1995341919 @default.
• W4224234949 cites W2084360277 @default.
• W4224234949 cites W2133990480 @default.
• W4224234949 cites W2152744490 @default.
• W4224234949 cites W2153635508 @default.
• W4224234949 cites W2169482951 @default.
• W4224234949 cites W2192381865 @default.
• W4224234949 cites W2285660444 @default.
• W4224234949 cites W2905519894 @default.
• W4224234949 cites W2912691033 @default.
• W4224234949 cites W2948425324 @default.
• W4224234949 cites W2972661888 @default.
• W4224234949 cites W2979963992 @default.
• W4224234949 cites W2993712737 @default.
• W4224234949 cites W2999585430 @default.
• W4224234949 cites W3006101764 @default.
• W4224234949 cites W3010389911 @default.
• W4224234949 cites W3019985288 @default.
• W4224234949 cites W3037682195 @default.
• W4224234949 cites W3040319990 @default.
• W4224234949 cites W3085447111 @default.
• W4224234949 cites W3087265011 @default.
• W4224234949 cites W3109153185 @default.
• W4224234949 cites W3110701973 @default.
• W4224234949 cites W3117963962 @default.
• W4224234949 cites W3121514681 @default.
• W4224234949 cites W3126460454 @default.
• W4224234949 cites W3163252910 @default.
• W4224234949 cites W3163262786 @default.
• W4224234949 cites W3167841307 @default.
• W4224234949 cites W3169689544 @default.
• W4224234949 cites W3184606595 @default.
• W4224234949 cites W3184772129 @default.
• W4224234949 cites W3195415980 @default.
• W4224234949 cites W4236137412 @default.
• W4224234949 cites W4239510810 @default.
• W4224234949 doi "https://doi.org/10.3390/electronics11081178" @default.
• W4224234949 hasPublicationYear "2022" @default.
• W4224234949 type Work @default.
• W4224234949 citedByCount "1" @default.
• W4224234949 countsByYear W42242349492022 @default.
• W4224234949 crossrefType "journal-article" @default.
• W4224234949 hasAuthorship W4224234949A5065879404 @default.
• W4224234949 hasAuthorship W4224234949A5066612315 @default.
• W4224234949 hasAuthorship W4224234949A5080935074 @default.
• W4224234949 hasBestOaLocation W42242349491 @default.
• W4224234949 hasConcept C108010975 @default.
• W4224234949 hasConcept C108583219 @default.
• W4224234949 hasConcept C113775141 @default.
• W4224234949 hasConcept C119857082 @default.
• W4224234949 hasConcept C12267149 @default.
• W4224234949 hasConcept C13164978 @default.
• W4224234949 hasConcept C13280743 @default.
• W4224234949 hasConcept C154945302 @default.
• W4224234949 hasConcept C157764524 @default.
• W4224234949 hasConcept C185798385 @default.
• W4224234949 hasConcept C205649164 @default.
• W4224234949 hasConcept C41008148 @default.
• W4224234949 hasConcept C42935608 @default.
• W4224234949 hasConcept C50644808 @default.
• W4224234949 hasConcept C555944384 @default.
• W4224234949 hasConcept C6557445 @default.
• W4224234949 hasConcept C76155785 @default.
• W4224234949 hasConcept C86803240 @default.
• W4224234949 hasConcept C9390403 @default.
• W4224234949 hasConceptScore W4224234949C108010975 @default.
• W4224234949 hasConceptScore W4224234949C108583219 @default.
• W4224234949 hasConceptScore W4224234949C113775141 @default.
• W4224234949 hasConceptScore W4224234949C119857082 @default.
• W4224234949 hasConceptScore W4224234949C12267149 @default.
• W4224234949 hasConceptScore W4224234949C13164978 @default.
• W4224234949 hasConceptScore W4224234949C13280743 @default.
• W4224234949 hasConceptScore W4224234949C154945302 @default.
• W4224234949 hasConceptScore W4224234949C157764524 @default.
• W4224234949 hasConceptScore W4224234949C185798385 @default.
• W4224234949 hasConceptScore W4224234949C205649164 @default.
• W4224234949 hasConceptScore W4224234949C41008148 @default.
• W4224234949 hasConceptScore W4224234949C42935608 @default.
• W4224234949 hasConceptScore W4224234949C50644808 @default.
• W4224234949 hasConceptScore W4224234949C555944384 @default.
• W4224234949 hasConceptScore W4224234949C6557445 @default.
• W4224234949 hasConceptScore W4224234949C76155785 @default.
• W4224234949 hasConceptScore W4224234949C86803240 @default.
• W4224234949 hasConceptScore W4224234949C9390403 @default.
• W4224234949 hasIssue "8" @default.
• W4224234949 hasLocation W42242349491 @default.
• W4224234949 hasOpenAccess W4224234949 @default.
• W4224234949 hasPrimaryLocation W42242349491 @default.
• W4224234949 hasRelatedWork W2795261237 @default.
• W4224234949 hasRelatedWork W3014300295 @default.

• next