FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216201614> ?p ?o ?g. }

• W3216201614 abstract "Due to the curse of dimensionality and the limitation on training data, approximating high-dimensional functions is a very challenging task even for powerful deep neural networks. Inspired by the Nonlinear Level set Learning (NLL) method that uses the reversible residual network (RevNet), in this paper we propose a new method of Dimension Reduction via Learning Level Sets (DRiLLS) for function approximation. Our method contains two major components: one is the pseudo-reversible neural network (PRNN) module that effectively transforms high-dimensional input variables to low-dimensional active variables, and the other is the synthesized regression module for approximating function values based on the transformed data in the low-dimensional space. The PRNN not only relaxes the invertibility constraint of the nonlinear transformation present in the NLL method due to the use of RevNet, but also adaptively weights the influence of each sample and controls the sensitivity of the function to the learned active variables. The synthesized regression uses Euclidean distance in the input space to select neighboring samples, whose projections on the space of active variables are used to perform local least-squares polynomial fitting. This helps to resolve numerical oscillation issues present in traditional local and global regressions. Extensive experimental results demonstrate that our DRiLLS method outperforms both the NLL and Active Subspace methods, especially when the target function possesses critical points in the interior of its input domain." @default.
• W3216201614 created "2021-12-06" @default.
• W3216201614 creator A5046509521 @default.
• W3216201614 creator A5049586233 @default.
• W3216201614 creator A5065454146 @default.
• W3216201614 creator A5075584064 @default.
• W3216201614 creator A5076382628 @default.
• W3216201614 date "2021-12-02" @default.
• W3216201614 modified "2023-09-26" @default.
• W3216201614 title "Level set learning with pseudo-reversible neural networks for nonlinear dimension reduction in function approximation" @default.
• W3216201614 cites W1603452536 @default.
• W3216201614 cites W1967692477 @default.
• W3216201614 cites W2001141328 @default.
• W3216201614 cites W2022215192 @default.
• W3216201614 cites W2030219534 @default.
• W3216201614 cites W2051669046 @default.
• W3216201614 cites W2053186076 @default.
• W3216201614 cites W2068752849 @default.
• W3216201614 cites W2087717467 @default.
• W3216201614 cites W2128728535 @default.
• W3216201614 cites W2144405862 @default.
• W3216201614 cites W2156838815 @default.
• W3216201614 cites W2161365042 @default.
• W3216201614 cites W2163490846 @default.
• W3216201614 cites W2399388063 @default.
• W3216201614 cites W2557283755 @default.
• W3216201614 cites W2625030036 @default.
• W3216201614 cites W2731103645 @default.
• W3216201614 cites W2734721340 @default.
• W3216201614 cites W2786232134 @default.
• W3216201614 cites W2895381778 @default.
• W3216201614 cites W2912649832 @default.
• W3216201614 cites W2963359731 @default.
• W3216201614 cites W2963684275 @default.
• W3216201614 cites W2964121744 @default.
• W3216201614 cites W2970963069 @default.
• W3216201614 cites W3020831715 @default.
• W3216201614 cites W3099161711 @default.
• W3216201614 cites W3159631644 @default.
• W3216201614 cites W3204708751 @default.
• W3216201614 doi "https://doi.org/10.48550/arxiv.2112.01438" @default.
• W3216201614 hasPublicationYear "2021" @default.
• W3216201614 type Work @default.
• W3216201614 sameAs 3216201614 @default.
• W3216201614 citedByCount "0" @default.
• W3216201614 crossrefType "posted-content" @default.
• W3216201614 hasAuthorship W3216201614A5046509521 @default.
• W3216201614 hasAuthorship W3216201614A5049586233 @default.
• W3216201614 hasAuthorship W3216201614A5065454146 @default.
• W3216201614 hasAuthorship W3216201614A5075584064 @default.
• W3216201614 hasAuthorship W3216201614A5076382628 @default.
• W3216201614 hasBestOaLocation W32162016141 @default.
• W3216201614 hasConcept C111030470 @default.
• W3216201614 hasConcept C111335779 @default.
• W3216201614 hasConcept C11413529 @default.
• W3216201614 hasConcept C121332964 @default.
• W3216201614 hasConcept C134306372 @default.
• W3216201614 hasConcept C14036430 @default.
• W3216201614 hasConcept C154945302 @default.
• W3216201614 hasConcept C158622935 @default.
• W3216201614 hasConcept C186450821 @default.
• W3216201614 hasConcept C202444582 @default.
• W3216201614 hasConcept C2524010 @default.
• W3216201614 hasConcept C32834561 @default.
• W3216201614 hasConcept C33676613 @default.
• W3216201614 hasConcept C33923547 @default.
• W3216201614 hasConcept C41008148 @default.
• W3216201614 hasConcept C50644808 @default.
• W3216201614 hasConcept C62520636 @default.
• W3216201614 hasConcept C70518039 @default.
• W3216201614 hasConcept C78458016 @default.
• W3216201614 hasConcept C86803240 @default.
• W3216201614 hasConcept C90119067 @default.
• W3216201614 hasConcept C91873725 @default.
• W3216201614 hasConceptScore W3216201614C111030470 @default.
• W3216201614 hasConceptScore W3216201614C111335779 @default.
• W3216201614 hasConceptScore W3216201614C11413529 @default.
• W3216201614 hasConceptScore W3216201614C121332964 @default.
• W3216201614 hasConceptScore W3216201614C134306372 @default.
• W3216201614 hasConceptScore W3216201614C14036430 @default.
• W3216201614 hasConceptScore W3216201614C154945302 @default.
• W3216201614 hasConceptScore W3216201614C158622935 @default.
• W3216201614 hasConceptScore W3216201614C186450821 @default.
• W3216201614 hasConceptScore W3216201614C202444582 @default.
• W3216201614 hasConceptScore W3216201614C2524010 @default.
• W3216201614 hasConceptScore W3216201614C32834561 @default.
• W3216201614 hasConceptScore W3216201614C33676613 @default.
• W3216201614 hasConceptScore W3216201614C33923547 @default.
• W3216201614 hasConceptScore W3216201614C41008148 @default.
• W3216201614 hasConceptScore W3216201614C50644808 @default.
• W3216201614 hasConceptScore W3216201614C62520636 @default.
• W3216201614 hasConceptScore W3216201614C70518039 @default.
• W3216201614 hasConceptScore W3216201614C78458016 @default.
• W3216201614 hasConceptScore W3216201614C86803240 @default.
• W3216201614 hasConceptScore W3216201614C90119067 @default.
• W3216201614 hasConceptScore W3216201614C91873725 @default.
• W3216201614 hasLocation W32162016141 @default.
• W3216201614 hasLocation W32162016142 @default.
• W3216201614 hasOpenAccess W3216201614 @default.
• W3216201614 hasPrimaryLocation W32162016141 @default.

• next