Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033967288> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3033967288 endingPage "1289" @default.
- W3033967288 startingPage "1289" @default.
- W3033967288 abstract "<p>Convolution represent basic layer in the convolutional neural network, but it<br />can result in big size of the data, which may increase the complexity of the<br />network. Different pooling methods are used to perform down sample these<br />data. In this paper, we have proposed a novel pooling method by using<br />Gaussian function to determine the wavelet filter coefficients . At first, the<br />basic statistics are determined for each pool size of the signal, then Gaussian<br />probability distribution function is determined . According to the procedure<br />of extracting the features , three methods are proposed , the first method is<br />used the normalized values of basic statistics as wavelet filter to be<br />multiplied by original signal, the second method used the determined<br />statistics as features of the original signal ,then multiplied it with constant<br />wavelet filter based on Gaussian ,while the third method is similar to first<br />method, except it depend on entire signal instead of each pool size. The<br />proposed methods are combined with other standard methods such as max<br />and pooling. The experiments are performed on different datasets , and the<br />results show that the proposed methods perform or outperform other<br />methods and can increase performance of the (CNN).</p>" @default.
- W3033967288 created "2020-06-12" @default.
- W3033967288 creator A5015422985 @default.
- W3033967288 creator A5031767911 @default.
- W3033967288 date "2020-12-01" @default.
- W3033967288 modified "2023-10-10" @default.
- W3033967288 title "A novel pooling layer based on gaussian function with wavelet transform" @default.
- W3033967288 doi "https://doi.org/10.11591/ijeecs.v20.i3.pp1289-1298" @default.
- W3033967288 hasPublicationYear "2020" @default.
- W3033967288 type Work @default.
- W3033967288 sameAs 3033967288 @default.
- W3033967288 citedByCount "1" @default.
- W3033967288 countsByYear W30339672882022 @default.
- W3033967288 crossrefType "journal-article" @default.
- W3033967288 hasAuthorship W3033967288A5015422985 @default.
- W3033967288 hasAuthorship W3033967288A5031767911 @default.
- W3033967288 hasBestOaLocation W30339672881 @default.
- W3033967288 hasConcept C105795698 @default.
- W3033967288 hasConcept C106131492 @default.
- W3033967288 hasConcept C11413529 @default.
- W3033967288 hasConcept C121332964 @default.
- W3033967288 hasConcept C14036430 @default.
- W3033967288 hasConcept C153180895 @default.
- W3033967288 hasConcept C154945302 @default.
- W3033967288 hasConcept C163716315 @default.
- W3033967288 hasConcept C31972630 @default.
- W3033967288 hasConcept C33923547 @default.
- W3033967288 hasConcept C41008148 @default.
- W3033967288 hasConcept C45347329 @default.
- W3033967288 hasConcept C47432892 @default.
- W3033967288 hasConcept C50644808 @default.
- W3033967288 hasConcept C62520636 @default.
- W3033967288 hasConcept C65892221 @default.
- W3033967288 hasConcept C70437156 @default.
- W3033967288 hasConcept C78458016 @default.
- W3033967288 hasConcept C86803240 @default.
- W3033967288 hasConceptScore W3033967288C105795698 @default.
- W3033967288 hasConceptScore W3033967288C106131492 @default.
- W3033967288 hasConceptScore W3033967288C11413529 @default.
- W3033967288 hasConceptScore W3033967288C121332964 @default.
- W3033967288 hasConceptScore W3033967288C14036430 @default.
- W3033967288 hasConceptScore W3033967288C153180895 @default.
- W3033967288 hasConceptScore W3033967288C154945302 @default.
- W3033967288 hasConceptScore W3033967288C163716315 @default.
- W3033967288 hasConceptScore W3033967288C31972630 @default.
- W3033967288 hasConceptScore W3033967288C33923547 @default.
- W3033967288 hasConceptScore W3033967288C41008148 @default.
- W3033967288 hasConceptScore W3033967288C45347329 @default.
- W3033967288 hasConceptScore W3033967288C47432892 @default.
- W3033967288 hasConceptScore W3033967288C50644808 @default.
- W3033967288 hasConceptScore W3033967288C62520636 @default.
- W3033967288 hasConceptScore W3033967288C65892221 @default.
- W3033967288 hasConceptScore W3033967288C70437156 @default.
- W3033967288 hasConceptScore W3033967288C78458016 @default.
- W3033967288 hasConceptScore W3033967288C86803240 @default.
- W3033967288 hasIssue "3" @default.
- W3033967288 hasLocation W30339672881 @default.
- W3033967288 hasLocation W30339672882 @default.
- W3033967288 hasOpenAccess W3033967288 @default.
- W3033967288 hasPrimaryLocation W30339672881 @default.
- W3033967288 hasRelatedWork W2009331049 @default.
- W3033967288 hasRelatedWork W2066418999 @default.
- W3033967288 hasRelatedWork W2071573116 @default.
- W3033967288 hasRelatedWork W2104155200 @default.
- W3033967288 hasRelatedWork W2379831516 @default.
- W3033967288 hasRelatedWork W2533586372 @default.
- W3033967288 hasRelatedWork W2609066529 @default.
- W3033967288 hasRelatedWork W2997558667 @default.
- W3033967288 hasRelatedWork W3127542252 @default.
- W3033967288 hasRelatedWork W4223479823 @default.
- W3033967288 hasVolume "20" @default.
- W3033967288 isParatext "false" @default.
- W3033967288 isRetracted "false" @default.
- W3033967288 magId "3033967288" @default.
- W3033967288 workType "article" @default.