Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805443695> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2805443695 abstract "Since a conceptor, achieving direction-selective damping of high-dimensional network signals, usually takes the form of a projection matrix and is deduced analytically, a conceptor-based neural network is thought to be untrainable with backpropagation and gradient-descent algorithms from end to end. It limits the application of conceptors. To address this issue, an algorithm is proposed to train conceptor-based neural networks from end to end with gradient-descent algorithms. To the best of the authors’ knowledge, it is the first work of such an end-to-end training algorithm. To develop this algorithm, a softmax-like loss function involved with conceptors is constructed empirically. Based on this loss function, corresponding gradients are deduced by using backpropagation method so that it is possible to train conceptor neural networks from end to end with a gradient-descent algorithm. Several experiments are conducted to show the feasibility and effectiveness of the proposed training algorithm." @default.
- W2805443695 created "2018-06-13" @default.
- W2805443695 creator A5007016042 @default.
- W2805443695 creator A5047903714 @default.
- W2805443695 creator A5084889194 @default.
- W2805443695 date "2018-07-01" @default.
- W2805443695 modified "2023-09-24" @default.
- W2805443695 title "End‐to‐end training algorithm for conceptor‐based neural networks" @default.
- W2805443695 cites W2100495367 @default.
- W2805443695 cites W2107878631 @default.
- W2805443695 cites W2112796928 @default.
- W2805443695 cites W2117539524 @default.
- W2805443695 cites W2136922672 @default.
- W2805443695 cites W2166049352 @default.
- W2805443695 doi "https://doi.org/10.1049/el.2018.0033" @default.
- W2805443695 hasPublicationYear "2018" @default.
- W2805443695 type Work @default.
- W2805443695 sameAs 2805443695 @default.
- W2805443695 citedByCount "2" @default.
- W2805443695 countsByYear W28054436952020 @default.
- W2805443695 countsByYear W28054436952021 @default.
- W2805443695 crossrefType "journal-article" @default.
- W2805443695 hasAuthorship W2805443695A5007016042 @default.
- W2805443695 hasAuthorship W2805443695A5047903714 @default.
- W2805443695 hasAuthorship W2805443695A5084889194 @default.
- W2805443695 hasConcept C11413529 @default.
- W2805443695 hasConcept C121332964 @default.
- W2805443695 hasConcept C14036430 @default.
- W2805443695 hasConcept C153258448 @default.
- W2805443695 hasConcept C153294291 @default.
- W2805443695 hasConcept C154945302 @default.
- W2805443695 hasConcept C155032097 @default.
- W2805443695 hasConcept C188441871 @default.
- W2805443695 hasConcept C2777211547 @default.
- W2805443695 hasConcept C41008148 @default.
- W2805443695 hasConcept C50644808 @default.
- W2805443695 hasConcept C74296488 @default.
- W2805443695 hasConcept C78458016 @default.
- W2805443695 hasConcept C86803240 @default.
- W2805443695 hasConceptScore W2805443695C11413529 @default.
- W2805443695 hasConceptScore W2805443695C121332964 @default.
- W2805443695 hasConceptScore W2805443695C14036430 @default.
- W2805443695 hasConceptScore W2805443695C153258448 @default.
- W2805443695 hasConceptScore W2805443695C153294291 @default.
- W2805443695 hasConceptScore W2805443695C154945302 @default.
- W2805443695 hasConceptScore W2805443695C155032097 @default.
- W2805443695 hasConceptScore W2805443695C188441871 @default.
- W2805443695 hasConceptScore W2805443695C2777211547 @default.
- W2805443695 hasConceptScore W2805443695C41008148 @default.
- W2805443695 hasConceptScore W2805443695C50644808 @default.
- W2805443695 hasConceptScore W2805443695C74296488 @default.
- W2805443695 hasConceptScore W2805443695C78458016 @default.
- W2805443695 hasConceptScore W2805443695C86803240 @default.
- W2805443695 hasFunder F4320321001 @default.
- W2805443695 hasFunder F4320326297 @default.
- W2805443695 hasLocation W28054436951 @default.
- W2805443695 hasOpenAccess W2805443695 @default.
- W2805443695 hasPrimaryLocation W28054436951 @default.
- W2805443695 hasRelatedWork W2058719832 @default.
- W2805443695 hasRelatedWork W2099604242 @default.
- W2805443695 hasRelatedWork W2115605526 @default.
- W2805443695 hasRelatedWork W2615915868 @default.
- W2805443695 hasRelatedWork W2805443695 @default.
- W2805443695 hasRelatedWork W3005627584 @default.
- W2805443695 hasRelatedWork W3155831151 @default.
- W2805443695 hasRelatedWork W3159389381 @default.
- W2805443695 hasRelatedWork W91712439 @default.
- W2805443695 hasRelatedWork W4287869072 @default.
- W2805443695 isParatext "false" @default.
- W2805443695 isRetracted "false" @default.
- W2805443695 magId "2805443695" @default.
- W2805443695 workType "article" @default.