FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950772912> ?p ?o ?g. }

• W2950772912 endingPage "105541" @default.
• W2950772912 startingPage "105541" @default.
• W2950772912 abstract "Abstract The conversion functions in the hidden layer of radial basis function neural networks (RBFNN) are Gaussian functions. The Gaussian functions are local to the kernel centers. In most of the existing research, the spatial local response of the sample is inaccurately calculated because the kernels have the same shape as a hypersphere, and the kernel parameters in the network are determined by experience. The influence of the fine structure in the local space is not considered during feature extraction. In addition, it is difficult to obtain a better feature extraction ability with less computational complexity. Therefore, this paper develops a multi-scale RBF kernel learning algorithm and proposes a new multi-layer RBF neural network model. For the samples of each class, the expectation maximization (EM) algorithm is used to obtain multi-layer nested sub-distribution models with different local response ranges, which are called multi-scale kernels in the network. The prior information of each sub-distribution is used as the connection weight between the multi-scale kernels. Finally, feature extraction is implemented using multi-layer kernel subspace embedding. The multi-scale kernel learning model can efficiently and accurately describe the fine structure of the samples and is fault tolerant to setting the number of kernels to a certain extent. Considering the prior probability of each kernel as the weight makes the feature extraction process satisfy the Bayes rule, which can enhance the interpretability of feature extraction in the network. This paper also theoretically proves that the proposed neural network is a generalized version of the original RBFNN. The experimental results show that the proposed method has better performance compared with some state-of-the-art algorithms." @default.
• W2950772912 created "2019-06-27" @default.
• W2950772912 creator A5048699364 @default.
• W2950772912 creator A5080063067 @default.
• W2950772912 creator A5082789325 @default.
• W2950772912 date "2019-09-01" @default.
• W2950772912 modified "2023-10-11" @default.
• W2950772912 title "Multi-layer radial basis function neural network based on multi-scale kernel learning" @default.
• W2950772912 cites W1486149594 @default.
• W2950772912 cites W1976047713 @default.
• W2950772912 cites W2003066679 @default.
• W2950772912 cites W2007836289 @default.
• W2950772912 cites W2024022568 @default.
• W2950772912 cites W2025713912 @default.
• W2950772912 cites W2064716744 @default.
• W2950772912 cites W2076586373 @default.
• W2950772912 cites W2121647436 @default.
• W2950772912 cites W2129648589 @default.
• W2950772912 cites W2138451337 @default.
• W2950772912 cites W2140095548 @default.
• W2950772912 cites W2141448031 @default.
• W2950772912 cites W2144847945 @default.
• W2950772912 cites W2158698691 @default.
• W2950772912 cites W2298860367 @default.
• W2950772912 cites W2306416933 @default.
• W2950772912 cites W2319954399 @default.
• W2950772912 cites W2359766982 @default.
• W2950772912 cites W2489777820 @default.
• W2950772912 cites W2534261280 @default.
• W2950772912 cites W2560381229 @default.
• W2950772912 cites W2606834215 @default.
• W2950772912 cites W2749412917 @default.
• W2950772912 cites W2794208198 @default.
• W2950772912 cites W397830089 @default.
• W2950772912 doi "https://doi.org/10.1016/j.asoc.2019.105541" @default.
• W2950772912 hasPublicationYear "2019" @default.
• W2950772912 type Work @default.
• W2950772912 sameAs 2950772912 @default.
• W2950772912 citedByCount "15" @default.
• W2950772912 countsByYear W29507729122020 @default.
• W2950772912 countsByYear W29507729122021 @default.
• W2950772912 countsByYear W29507729122022 @default.
• W2950772912 countsByYear W29507729122023 @default.
• W2950772912 crossrefType "journal-article" @default.
• W2950772912 hasAuthorship W2950772912A5048699364 @default.
• W2950772912 hasAuthorship W2950772912A5080063067 @default.
• W2950772912 hasAuthorship W2950772912A5082789325 @default.
• W2950772912 hasConcept C114614502 @default.
• W2950772912 hasConcept C121332964 @default.
• W2950772912 hasConcept C122280245 @default.
• W2950772912 hasConcept C12267149 @default.
• W2950772912 hasConcept C12426560 @default.
• W2950772912 hasConcept C132917294 @default.
• W2950772912 hasConcept C153180895 @default.
• W2950772912 hasConcept C154945302 @default.
• W2950772912 hasConcept C159985019 @default.
• W2950772912 hasConcept C192562407 @default.
• W2950772912 hasConcept C2524010 @default.
• W2950772912 hasConcept C2778755073 @default.
• W2950772912 hasConcept C2779227376 @default.
• W2950772912 hasConcept C33923547 @default.
• W2950772912 hasConcept C41008148 @default.
• W2950772912 hasConcept C50644808 @default.
• W2950772912 hasConcept C62520636 @default.
• W2950772912 hasConcept C74193536 @default.
• W2950772912 hasConcept C75866337 @default.
• W2950772912 hasConcept C98856871 @default.
• W2950772912 hasConceptScore W2950772912C114614502 @default.
• W2950772912 hasConceptScore W2950772912C121332964 @default.
• W2950772912 hasConceptScore W2950772912C122280245 @default.
• W2950772912 hasConceptScore W2950772912C12267149 @default.
• W2950772912 hasConceptScore W2950772912C12426560 @default.
• W2950772912 hasConceptScore W2950772912C132917294 @default.
• W2950772912 hasConceptScore W2950772912C153180895 @default.
• W2950772912 hasConceptScore W2950772912C154945302 @default.
• W2950772912 hasConceptScore W2950772912C159985019 @default.
• W2950772912 hasConceptScore W2950772912C192562407 @default.
• W2950772912 hasConceptScore W2950772912C2524010 @default.
• W2950772912 hasConceptScore W2950772912C2778755073 @default.
• W2950772912 hasConceptScore W2950772912C2779227376 @default.
• W2950772912 hasConceptScore W2950772912C33923547 @default.
• W2950772912 hasConceptScore W2950772912C41008148 @default.
• W2950772912 hasConceptScore W2950772912C50644808 @default.
• W2950772912 hasConceptScore W2950772912C62520636 @default.
• W2950772912 hasConceptScore W2950772912C74193536 @default.
• W2950772912 hasConceptScore W2950772912C75866337 @default.
• W2950772912 hasConceptScore W2950772912C98856871 @default.
• W2950772912 hasFunder F4320321001 @default.
• W2950772912 hasFunder F4320325571 @default.
• W2950772912 hasFunder F4320326705 @default.
• W2950772912 hasLocation W29507729121 @default.
• W2950772912 hasOpenAccess W2950772912 @default.
• W2950772912 hasPrimaryLocation W29507729121 @default.
• W2950772912 hasRelatedWork W1963582092 @default.
• W2950772912 hasRelatedWork W2019243908 @default.
• W2950772912 hasRelatedWork W2027376491 @default.
• W2950772912 hasRelatedWork W2032884154 @default.
• W2950772912 hasRelatedWork W2042014600 @default.

• next