FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205873250> ?p ?o ?g. }

• W3205873250 abstract "Recently, the method that learns networks layer by layer has attracted increasing interest for its ease of analysis. For the method, the main challenge lies in deriving an optimization target for each layer by inversely propagating the global target of the network. The target propagation is an ill-posed problem, due to involving the inversion of nonlinear activations from low-dimensional to high-dimensional spaces. To address the problem, the existing solution is to learn an auxiliary network to specially propagate the target. However, the network lacks stability, and moreover, it leads to higher complexity for network learning. In the letter, we show that target propagation could be achieved by modeling the network's each layer with compressed sensing, without the need of auxiliary networks. Experiments show that the proposed method could achieve better performance than the auxiliary network-based method.<br>" @default.
• W3205873250 created "2021-10-25" @default.
• W3205873250 creator A5032223248 @default.
• W3205873250 creator A5050040890 @default.
• W3205873250 creator A5081599861 @default.
• W3205873250 creator A5088357715 @default.
• W3205873250 date "2021-10-25" @default.
• W3205873250 modified "2023-09-27" @default.
• W3205873250 title "Cascaded Compressed Sensing Networks: A Reversible Architecture for Layerwise Learning" @default.
• W3205873250 cites W1606458877 @default.
• W3205873250 cites W1855112655 @default.
• W3205873250 cites W1971402995 @default.
• W3205873250 cites W1973631422 @default.
• W3205873250 cites W1993273815 @default.
• W3205873250 cites W2057069782 @default.
• W3205873250 cites W2078204800 @default.
• W3205873250 cites W2108598243 @default.
• W3205873250 cites W2122825543 @default.
• W3205873250 cites W2128659236 @default.
• W3205873250 cites W2129131372 @default.
• W3205873250 cites W2130187411 @default.
• W3205873250 cites W2135046866 @default.
• W3205873250 cites W2136235822 @default.
• W3205873250 cites W2154332973 @default.
• W3205873250 cites W2158581396 @default.
• W3205873250 cites W2161305109 @default.
• W3205873250 cites W2163605009 @default.
• W3205873250 cites W2164452299 @default.
• W3205873250 cites W2182396527 @default.
• W3205873250 cites W2604117713 @default.
• W3205873250 cites W2788295695 @default.
• W3205873250 cites W2906532716 @default.
• W3205873250 cites W2906967080 @default.
• W3205873250 cites W2911586496 @default.
• W3205873250 cites W2952448932 @default.
• W3205873250 cites W2963047948 @default.
• W3205873250 cites W2963534251 @default.
• W3205873250 cites W2979473749 @default.
• W3205873250 cites W2993510279 @default.
• W3205873250 cites W2995268367 @default.
• W3205873250 cites W3116512656 @default.
• W3205873250 cites W3118608800 @default.
• W3205873250 doi "https://doi.org/10.36227/techrxiv.16865041" @default.
• W3205873250 hasPublicationYear "2021" @default.
• W3205873250 type Work @default.
• W3205873250 sameAs 3205873250 @default.
• W3205873250 citedByCount "0" @default.
• W3205873250 crossrefType "posted-content" @default.
• W3205873250 hasAuthorship W3205873250A5032223248 @default.
• W3205873250 hasAuthorship W3205873250A5050040890 @default.
• W3205873250 hasAuthorship W3205873250A5081599861 @default.
• W3205873250 hasAuthorship W3205873250A5088357715 @default.
• W3205873250 hasBestOaLocation W32058732501 @default.
• W3205873250 hasConcept C109007969 @default.
• W3205873250 hasConcept C112972136 @default.
• W3205873250 hasConcept C11413529 @default.
• W3205873250 hasConcept C119857082 @default.
• W3205873250 hasConcept C120314980 @default.
• W3205873250 hasConcept C121332964 @default.
• W3205873250 hasConcept C124851039 @default.
• W3205873250 hasConcept C151730666 @default.
• W3205873250 hasConcept C154945302 @default.
• W3205873250 hasConcept C158622935 @default.
• W3205873250 hasConcept C159985019 @default.
• W3205873250 hasConcept C1893757 @default.
• W3205873250 hasConcept C192562407 @default.
• W3205873250 hasConcept C193415008 @default.
• W3205873250 hasConcept C2779227376 @default.
• W3205873250 hasConcept C31258907 @default.
• W3205873250 hasConcept C41008148 @default.
• W3205873250 hasConcept C62520636 @default.
• W3205873250 hasConcept C86803240 @default.
• W3205873250 hasConceptScore W3205873250C109007969 @default.
• W3205873250 hasConceptScore W3205873250C112972136 @default.
• W3205873250 hasConceptScore W3205873250C11413529 @default.
• W3205873250 hasConceptScore W3205873250C119857082 @default.
• W3205873250 hasConceptScore W3205873250C120314980 @default.
• W3205873250 hasConceptScore W3205873250C121332964 @default.
• W3205873250 hasConceptScore W3205873250C124851039 @default.
• W3205873250 hasConceptScore W3205873250C151730666 @default.
• W3205873250 hasConceptScore W3205873250C154945302 @default.
• W3205873250 hasConceptScore W3205873250C158622935 @default.
• W3205873250 hasConceptScore W3205873250C159985019 @default.
• W3205873250 hasConceptScore W3205873250C1893757 @default.
• W3205873250 hasConceptScore W3205873250C192562407 @default.
• W3205873250 hasConceptScore W3205873250C193415008 @default.
• W3205873250 hasConceptScore W3205873250C2779227376 @default.
• W3205873250 hasConceptScore W3205873250C31258907 @default.
• W3205873250 hasConceptScore W3205873250C41008148 @default.
• W3205873250 hasConceptScore W3205873250C62520636 @default.
• W3205873250 hasConceptScore W3205873250C86803240 @default.
• W3205873250 hasLocation W32058732501 @default.
• W3205873250 hasLocation W32058732502 @default.
• W3205873250 hasLocation W32058732503 @default.
• W3205873250 hasOpenAccess W3205873250 @default.
• W3205873250 hasPrimaryLocation W32058732501 @default.
• W3205873250 hasRelatedWork W1540753034 @default.
• W3205873250 hasRelatedWork W1587227328 @default.
• W3205873250 hasRelatedWork W1596201972 @default.
• W3205873250 hasRelatedWork W1967954938 @default.

• next