Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128753387> ?p ?o ?g. }
- W3128753387 abstract "Dimension of the encoder output (i.e., the code layer) in an autoencoder is a key hyper-parameter for representing the input data in a proper space. This dimension must be carefully selected in order to guarantee the desired reconstruction accuracy. Although overcomplete representation can address this dimension issue, the computational complexity will increase with dimension. Inspired by non-parametric methods, here, we propose a metalearning approach to increase the number of basis vectors used in dynamic sparse coding on the fly. An actor-critic algorithm is deployed to automatically choose an appropriate dimension for feature vectors regarding the required level of accuracy. The proposed method benefits from online dictionary learning and fast iterative shrinkage-thresholding algorithm (FISTA) as the optimizer in the inference phase. It aims at choosing the minimum number of bases for the overcomplete representation regarding the reconstruction error threshold. This method allows for online controlling of both the representation dimension and the reconstruction error in a dynamic framework." @default.
- W3128753387 created "2021-02-15" @default.
- W3128753387 creator A5004572627 @default.
- W3128753387 creator A5048296786 @default.
- W3128753387 creator A5062342303 @default.
- W3128753387 creator A5072264935 @default.
- W3128753387 date "2021-01-30" @default.
- W3128753387 modified "2023-09-27" @default.
- W3128753387 title "Metalearning: Sparse Variable-Structure Automata." @default.
- W3128753387 cites W1593784033 @default.
- W3128753387 cites W1853900790 @default.
- W3128753387 cites W1922442141 @default.
- W3128753387 cites W1987191478 @default.
- W3128753387 cites W1997017524 @default.
- W3128753387 cites W2005876975 @default.
- W3128753387 cites W2008732654 @default.
- W3128753387 cites W2013145725 @default.
- W3128753387 cites W2021659075 @default.
- W3128753387 cites W2084650738 @default.
- W3128753387 cites W2098522416 @default.
- W3128753387 cites W2113606819 @default.
- W3128753387 cites W2121830132 @default.
- W3128753387 cites W2145889472 @default.
- W3128753387 cites W2150341604 @default.
- W3128753387 cites W2295322694 @default.
- W3128753387 cites W2331334294 @default.
- W3128753387 cites W2559924584 @default.
- W3128753387 cites W2750889120 @default.
- W3128753387 cites W2755502793 @default.
- W3128753387 cites W2773809991 @default.
- W3128753387 cites W2786383677 @default.
- W3128753387 cites W2792311129 @default.
- W3128753387 cites W2801171494 @default.
- W3128753387 cites W2805077925 @default.
- W3128753387 cites W2946004135 @default.
- W3128753387 cites W2963087201 @default.
- W3128753387 cites W2963194771 @default.
- W3128753387 cites W3103871196 @default.
- W3128753387 hasPublicationYear "2021" @default.
- W3128753387 type Work @default.
- W3128753387 sameAs 3128753387 @default.
- W3128753387 citedByCount "0" @default.
- W3128753387 crossrefType "posted-content" @default.
- W3128753387 hasAuthorship W3128753387A5004572627 @default.
- W3128753387 hasAuthorship W3128753387A5048296786 @default.
- W3128753387 hasAuthorship W3128753387A5062342303 @default.
- W3128753387 hasAuthorship W3128753387A5072264935 @default.
- W3128753387 hasConcept C101738243 @default.
- W3128753387 hasConcept C105795698 @default.
- W3128753387 hasConcept C111919701 @default.
- W3128753387 hasConcept C11413529 @default.
- W3128753387 hasConcept C117251300 @default.
- W3128753387 hasConcept C118505674 @default.
- W3128753387 hasConcept C124066611 @default.
- W3128753387 hasConcept C153180895 @default.
- W3128753387 hasConcept C154945302 @default.
- W3128753387 hasConcept C17744445 @default.
- W3128753387 hasConcept C199539241 @default.
- W3128753387 hasConcept C202444582 @default.
- W3128753387 hasConcept C2776214188 @default.
- W3128753387 hasConcept C2776359362 @default.
- W3128753387 hasConcept C33676613 @default.
- W3128753387 hasConcept C33923547 @default.
- W3128753387 hasConcept C41008148 @default.
- W3128753387 hasConcept C50644808 @default.
- W3128753387 hasConcept C77637269 @default.
- W3128753387 hasConcept C80444323 @default.
- W3128753387 hasConcept C83665646 @default.
- W3128753387 hasConcept C94625758 @default.
- W3128753387 hasConceptScore W3128753387C101738243 @default.
- W3128753387 hasConceptScore W3128753387C105795698 @default.
- W3128753387 hasConceptScore W3128753387C111919701 @default.
- W3128753387 hasConceptScore W3128753387C11413529 @default.
- W3128753387 hasConceptScore W3128753387C117251300 @default.
- W3128753387 hasConceptScore W3128753387C118505674 @default.
- W3128753387 hasConceptScore W3128753387C124066611 @default.
- W3128753387 hasConceptScore W3128753387C153180895 @default.
- W3128753387 hasConceptScore W3128753387C154945302 @default.
- W3128753387 hasConceptScore W3128753387C17744445 @default.
- W3128753387 hasConceptScore W3128753387C199539241 @default.
- W3128753387 hasConceptScore W3128753387C202444582 @default.
- W3128753387 hasConceptScore W3128753387C2776214188 @default.
- W3128753387 hasConceptScore W3128753387C2776359362 @default.
- W3128753387 hasConceptScore W3128753387C33676613 @default.
- W3128753387 hasConceptScore W3128753387C33923547 @default.
- W3128753387 hasConceptScore W3128753387C41008148 @default.
- W3128753387 hasConceptScore W3128753387C50644808 @default.
- W3128753387 hasConceptScore W3128753387C77637269 @default.
- W3128753387 hasConceptScore W3128753387C80444323 @default.
- W3128753387 hasConceptScore W3128753387C83665646 @default.
- W3128753387 hasConceptScore W3128753387C94625758 @default.
- W3128753387 hasLocation W31287533871 @default.
- W3128753387 hasOpenAccess W3128753387 @default.
- W3128753387 hasPrimaryLocation W31287533871 @default.
- W3128753387 hasRelatedWork W1567378200 @default.
- W3128753387 hasRelatedWork W2154321958 @default.
- W3128753387 hasRelatedWork W215874021 @default.
- W3128753387 hasRelatedWork W2297137102 @default.
- W3128753387 hasRelatedWork W2339361910 @default.
- W3128753387 hasRelatedWork W2344303854 @default.