Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554631982> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2554631982 abstract "When large models are used for a classification task, model compres- sion is necessary because there are transmission, space, time or computing con- straints that have to be fulfilled. Multilayer Perceptron (MLP) models are tradi- tionally used as a classifier, but depending on the problem, they may need a large number of parameters (neuron functions, weights and bias) to obtain an accept- able performance. This work extends the evaluation of a technique to compress an array of MLPs, through the outputs of a Volterra-Neural Network (Volterra-NN), maintaining its classification performance. The obtained results show that these outputs can be used to build an array of (Volterra-NN) that needs significantly less parameters than the original array of MLPs, furthermore having the same high ac- curacy in most of the cases. The Volterra-NN compression capabilities have been tested by solving several kind of classification problems. Experimental results are presented on three well-known databases: Letter Recognition, Pen-Based Recog- nition of Handwritten Digits, and Face recognition databases." @default.
- W2554631982 created "2016-11-30" @default.
- W2554631982 creator A5013986713 @default.
- W2554631982 date "2012-01-01" @default.
- W2554631982 modified "2023-09-27" @default.
- W2554631982 title "Extended evaluation of the Volterra-Neural Network for model compression" @default.
- W2554631982 cites W1615672776 @default.
- W2554631982 cites W1968528416 @default.
- W2554631982 cites W1982612521 @default.
- W2554631982 cites W2023294425 @default.
- W2554631982 cites W2048201040 @default.
- W2554631982 cites W2062638654 @default.
- W2554631982 cites W2073934641 @default.
- W2554631982 cites W2087070363 @default.
- W2554631982 cites W2124776405 @default.
- W2554631982 cites W2145946289 @default.
- W2554631982 cites W2147564534 @default.
- W2554631982 cites W2155729921 @default.
- W2554631982 cites W2168665295 @default.
- W2554631982 cites W2294370754 @default.
- W2554631982 cites W2598306943 @default.
- W2554631982 cites W3017143921 @default.
- W2554631982 hasPublicationYear "2012" @default.
- W2554631982 type Work @default.
- W2554631982 sameAs 2554631982 @default.
- W2554631982 citedByCount "0" @default.
- W2554631982 crossrefType "journal-article" @default.
- W2554631982 hasAuthorship W2554631982A5013986713 @default.
- W2554631982 hasConcept C119857082 @default.
- W2554631982 hasConcept C121332964 @default.
- W2554631982 hasConcept C153180895 @default.
- W2554631982 hasConcept C154945302 @default.
- W2554631982 hasConcept C158622935 @default.
- W2554631982 hasConcept C179717631 @default.
- W2554631982 hasConcept C2983756050 @default.
- W2554631982 hasConcept C41008148 @default.
- W2554631982 hasConcept C50644808 @default.
- W2554631982 hasConcept C60908668 @default.
- W2554631982 hasConcept C62520636 @default.
- W2554631982 hasConcept C95623464 @default.
- W2554631982 hasConceptScore W2554631982C119857082 @default.
- W2554631982 hasConceptScore W2554631982C121332964 @default.
- W2554631982 hasConceptScore W2554631982C153180895 @default.
- W2554631982 hasConceptScore W2554631982C154945302 @default.
- W2554631982 hasConceptScore W2554631982C158622935 @default.
- W2554631982 hasConceptScore W2554631982C179717631 @default.
- W2554631982 hasConceptScore W2554631982C2983756050 @default.
- W2554631982 hasConceptScore W2554631982C41008148 @default.
- W2554631982 hasConceptScore W2554631982C50644808 @default.
- W2554631982 hasConceptScore W2554631982C60908668 @default.
- W2554631982 hasConceptScore W2554631982C62520636 @default.
- W2554631982 hasConceptScore W2554631982C95623464 @default.
- W2554631982 hasLocation W25546319821 @default.
- W2554631982 hasOpenAccess W2554631982 @default.
- W2554631982 hasPrimaryLocation W25546319821 @default.
- W2554631982 hasRelatedWork W1443987605 @default.
- W2554631982 hasRelatedWork W1501894702 @default.
- W2554631982 hasRelatedWork W1617445017 @default.
- W2554631982 hasRelatedWork W1849930441 @default.
- W2554631982 hasRelatedWork W1938722960 @default.
- W2554631982 hasRelatedWork W2043208871 @default.
- W2554631982 hasRelatedWork W2079711499 @default.
- W2554631982 hasRelatedWork W2106224199 @default.
- W2554631982 hasRelatedWork W2118259313 @default.
- W2554631982 hasRelatedWork W2118277177 @default.
- W2554631982 hasRelatedWork W2121839474 @default.
- W2554631982 hasRelatedWork W2149510713 @default.
- W2554631982 hasRelatedWork W2188084331 @default.
- W2554631982 hasRelatedWork W2280021902 @default.
- W2554631982 hasRelatedWork W2771675948 @default.
- W2554631982 hasRelatedWork W3024043231 @default.
- W2554631982 hasRelatedWork W3105788079 @default.
- W2554631982 hasRelatedWork W58244977 @default.
- W2554631982 hasRelatedWork W2158119771 @default.
- W2554631982 hasRelatedWork W3146409626 @default.
- W2554631982 isParatext "false" @default.
- W2554631982 isRetracted "false" @default.
- W2554631982 magId "2554631982" @default.
- W2554631982 workType "article" @default.