Matches in SemOpenAlex for { <https://semopenalex.org/work/W2379789024> ?p ?o ?g. }
- W2379789024 endingPage "1264" @default.
- W2379789024 startingPage "1249" @default.
- W2379789024 abstract "In visual modeling, invariance properties of visual cells are often explained by a pooling mechanism, in which outputs of neurons with similar selectivities to some stimulus parameters are integrated so as to gain some extent of invariance to other parameters. For example, the classical energy model of phase-invariant V1 complex cells pools model simple cells preferring similar orientation but different phases. Prior studies, such as independent subspace analysis, have shown that phase-invariance properties of V1 complex cells can be learned from spatial statistics of natural inputs. However, those previous approaches assumed a squaring nonlinearity on the neural outputs to capture energy correlation; such nonlinearity is arguably unnatural from a neurobiological viewpoint but hard to change due to its tight integration into their formalisms. Moreover, they used somewhat complicated objective functions requiring expensive computations for optimization. In this study, we show that visual spatial pooling can be learned in a much simpler way using strong dimension reduction based on principal component analysis. This approach learns to ignore a large part of detailed spatial structure of the input and thereby estimates a linear pooling matrix. Using this framework, we demonstrate that pooling of model V1 simple cells learned in this way, even with nonlinearities other than squaring, can reproduce standard tuning properties of V1 complex cells. For further understanding, we analyze several variants of the pooling model and argue that a reasonable pooling can generally be obtained from any kind of linear transformation that retains several of the first principal components and suppresses the remaining ones. In particular, we show how the classic Wiener filtering theory leads to one such variant." @default.
- W2379789024 created "2016-06-24" @default.
- W2379789024 creator A5025142030 @default.
- W2379789024 creator A5061498233 @default.
- W2379789024 date "2016-07-01" @default.
- W2379789024 modified "2023-09-26" @default.
- W2379789024 title "Learning Visual Spatial Pooling by Strong PCA Dimension Reduction" @default.
- W2379789024 cites W104847522 @default.
- W2379789024 cites W1605102919 @default.
- W2379789024 cites W1971017968 @default.
- W2379789024 cites W1985520156 @default.
- W2379789024 cites W1988139867 @default.
- W2379789024 cites W2008370690 @default.
- W2379789024 cites W2020604100 @default.
- W2379789024 cites W2027914108 @default.
- W2379789024 cites W2039984860 @default.
- W2379789024 cites W2050583479 @default.
- W2379789024 cites W2057221085 @default.
- W2379789024 cites W2062690756 @default.
- W2379789024 cites W2096388912 @default.
- W2379789024 cites W2101926813 @default.
- W2379789024 cites W2101933716 @default.
- W2379789024 cites W2106451016 @default.
- W2379789024 cites W2108992228 @default.
- W2379789024 cites W2116360511 @default.
- W2379789024 cites W2116365953 @default.
- W2379789024 cites W2118453814 @default.
- W2379789024 cites W2124486835 @default.
- W2379789024 cites W2129217160 @default.
- W2379789024 cites W2134309959 @default.
- W2379789024 cites W2135587681 @default.
- W2379789024 cites W2137234026 @default.
- W2379789024 cites W2141224535 @default.
- W2379789024 cites W2142457795 @default.
- W2379789024 cites W2142615865 @default.
- W2379789024 cites W2145889472 @default.
- W2379789024 cites W2146444479 @default.
- W2379789024 cites W2148553367 @default.
- W2379789024 cites W2149194912 @default.
- W2379789024 cites W2169394305 @default.
- W2379789024 cites W4240480640 @default.
- W2379789024 cites W4241395986 @default.
- W2379789024 cites W4243035954 @default.
- W2379789024 doi "https://doi.org/10.1162/neco_a_00843" @default.
- W2379789024 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/27171856" @default.
- W2379789024 hasPublicationYear "2016" @default.
- W2379789024 type Work @default.
- W2379789024 sameAs 2379789024 @default.
- W2379789024 citedByCount "28" @default.
- W2379789024 countsByYear W23797890242016 @default.
- W2379789024 countsByYear W23797890242017 @default.
- W2379789024 countsByYear W23797890242018 @default.
- W2379789024 countsByYear W23797890242019 @default.
- W2379789024 countsByYear W23797890242020 @default.
- W2379789024 countsByYear W23797890242021 @default.
- W2379789024 countsByYear W23797890242022 @default.
- W2379789024 countsByYear W23797890242023 @default.
- W2379789024 crossrefType "journal-article" @default.
- W2379789024 hasAuthorship W2379789024A5025142030 @default.
- W2379789024 hasAuthorship W2379789024A5061498233 @default.
- W2379789024 hasConcept C11413529 @default.
- W2379789024 hasConcept C121332964 @default.
- W2379789024 hasConcept C153180895 @default.
- W2379789024 hasConcept C154945302 @default.
- W2379789024 hasConcept C158622935 @default.
- W2379789024 hasConcept C171018156 @default.
- W2379789024 hasConcept C190470478 @default.
- W2379789024 hasConcept C2524010 @default.
- W2379789024 hasConcept C27438332 @default.
- W2379789024 hasConcept C33923547 @default.
- W2379789024 hasConcept C37914503 @default.
- W2379789024 hasConcept C3832189 @default.
- W2379789024 hasConcept C41008148 @default.
- W2379789024 hasConcept C45374587 @default.
- W2379789024 hasConcept C50644808 @default.
- W2379789024 hasConcept C62520636 @default.
- W2379789024 hasConcept C70437156 @default.
- W2379789024 hasConcept C70518039 @default.
- W2379789024 hasConceptScore W2379789024C11413529 @default.
- W2379789024 hasConceptScore W2379789024C121332964 @default.
- W2379789024 hasConceptScore W2379789024C153180895 @default.
- W2379789024 hasConceptScore W2379789024C154945302 @default.
- W2379789024 hasConceptScore W2379789024C158622935 @default.
- W2379789024 hasConceptScore W2379789024C171018156 @default.
- W2379789024 hasConceptScore W2379789024C190470478 @default.
- W2379789024 hasConceptScore W2379789024C2524010 @default.
- W2379789024 hasConceptScore W2379789024C27438332 @default.
- W2379789024 hasConceptScore W2379789024C33923547 @default.
- W2379789024 hasConceptScore W2379789024C37914503 @default.
- W2379789024 hasConceptScore W2379789024C3832189 @default.
- W2379789024 hasConceptScore W2379789024C41008148 @default.
- W2379789024 hasConceptScore W2379789024C45374587 @default.
- W2379789024 hasConceptScore W2379789024C50644808 @default.
- W2379789024 hasConceptScore W2379789024C62520636 @default.
- W2379789024 hasConceptScore W2379789024C70437156 @default.
- W2379789024 hasConceptScore W2379789024C70518039 @default.
- W2379789024 hasIssue "7" @default.
- W2379789024 hasLocation W23797890241 @default.