Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913812556> ?p ?o ?g. }
- W2913812556 endingPage "17206" @default.
- W2913812556 startingPage "17195" @default.
- W2913812556 abstract "Unsupervised feature learning via auto-encoders results in low-dimensional representations in latent space that capture the patterns of input data. The auto-encoders with robust regularization learn qualified features that are less sensitive to small perturbations of inputs. However, the previous robust auto-encoders highly depend on pre-defined structure settings and often learn full-connected networks that are easily prone to over-fitting. To solve the above limitations, we propose in this paper an explicitly regularized framework which improves the sparsity and flexibility of robust auto-encoders. First, our model encourages the activation functions to automatically adjust themselves between linear and non-linear ones. Second, the mapping functions of the encoder are constrained by group sparsity and exclusive sparsity to reduce the redundancy of parameters. The proximal gradient method is used to optimize our model since the objective function contains non-smooth components. We conduct experiments in single-layer and multiple-layer auto-encoders in the classification task. The numerical results show that our model achieves better accuracy than baseline models. Our method also shows better performance in denoising task." @default.
- W2913812556 created "2019-02-21" @default.
- W2913812556 creator A5008708386 @default.
- W2913812556 creator A5011194717 @default.
- W2913812556 creator A5019041750 @default.
- W2913812556 creator A5069927107 @default.
- W2913812556 date "2019-01-01" @default.
- W2913812556 modified "2023-10-15" @default.
- W2913812556 title "Learning Robust Auto-Encoders With Regularizer for Linearity and Sparsity" @default.
- W2913812556 cites W1724038983 @default.
- W2913812556 cites W1925417509 @default.
- W2913812556 cites W1973681148 @default.
- W2913812556 cites W1987371344 @default.
- W2913812556 cites W2025768430 @default.
- W2913812556 cites W2050752817 @default.
- W2913812556 cites W2100495367 @default.
- W2913812556 cites W2112796928 @default.
- W2913812556 cites W2120480077 @default.
- W2913812556 cites W2130325614 @default.
- W2913812556 cites W2135046866 @default.
- W2913812556 cites W2136922672 @default.
- W2913812556 cites W2138019504 @default.
- W2913812556 cites W2163922914 @default.
- W2913812556 cites W2165720259 @default.
- W2913812556 cites W2275445006 @default.
- W2913812556 cites W2318949783 @default.
- W2913812556 cites W2321627895 @default.
- W2913812556 cites W2393319904 @default.
- W2913812556 cites W2511630356 @default.
- W2913812556 cites W2613053618 @default.
- W2913812556 cites W2743138268 @default.
- W2913812556 cites W2798991696 @default.
- W2913812556 cites W2804196292 @default.
- W2913812556 cites W2963521312 @default.
- W2913812556 cites W4244393449 @default.
- W2913812556 doi "https://doi.org/10.1109/access.2019.2895884" @default.
- W2913812556 hasPublicationYear "2019" @default.
- W2913812556 type Work @default.
- W2913812556 sameAs 2913812556 @default.
- W2913812556 citedByCount "8" @default.
- W2913812556 countsByYear W29138125562019 @default.
- W2913812556 countsByYear W29138125562020 @default.
- W2913812556 countsByYear W29138125562021 @default.
- W2913812556 countsByYear W29138125562023 @default.
- W2913812556 crossrefType "journal-article" @default.
- W2913812556 hasAuthorship W2913812556A5008708386 @default.
- W2913812556 hasAuthorship W2913812556A5011194717 @default.
- W2913812556 hasAuthorship W2913812556A5019041750 @default.
- W2913812556 hasAuthorship W2913812556A5069927107 @default.
- W2913812556 hasBestOaLocation W29138125561 @default.
- W2913812556 hasConcept C101738243 @default.
- W2913812556 hasConcept C104317684 @default.
- W2913812556 hasConcept C108583219 @default.
- W2913812556 hasConcept C111919701 @default.
- W2913812556 hasConcept C11413529 @default.
- W2913812556 hasConcept C118505674 @default.
- W2913812556 hasConcept C125411270 @default.
- W2913812556 hasConcept C152124472 @default.
- W2913812556 hasConcept C153180895 @default.
- W2913812556 hasConcept C154945302 @default.
- W2913812556 hasConcept C185592680 @default.
- W2913812556 hasConcept C2776135515 @default.
- W2913812556 hasConcept C41008148 @default.
- W2913812556 hasConcept C55493867 @default.
- W2913812556 hasConcept C63479239 @default.
- W2913812556 hasConceptScore W2913812556C101738243 @default.
- W2913812556 hasConceptScore W2913812556C104317684 @default.
- W2913812556 hasConceptScore W2913812556C108583219 @default.
- W2913812556 hasConceptScore W2913812556C111919701 @default.
- W2913812556 hasConceptScore W2913812556C11413529 @default.
- W2913812556 hasConceptScore W2913812556C118505674 @default.
- W2913812556 hasConceptScore W2913812556C125411270 @default.
- W2913812556 hasConceptScore W2913812556C152124472 @default.
- W2913812556 hasConceptScore W2913812556C153180895 @default.
- W2913812556 hasConceptScore W2913812556C154945302 @default.
- W2913812556 hasConceptScore W2913812556C185592680 @default.
- W2913812556 hasConceptScore W2913812556C2776135515 @default.
- W2913812556 hasConceptScore W2913812556C41008148 @default.
- W2913812556 hasConceptScore W2913812556C55493867 @default.
- W2913812556 hasConceptScore W2913812556C63479239 @default.
- W2913812556 hasFunder F4320321001 @default.
- W2913812556 hasFunder F4320326972 @default.
- W2913812556 hasLocation W29138125561 @default.
- W2913812556 hasLocation W29138125562 @default.
- W2913812556 hasOpenAccess W2913812556 @default.
- W2913812556 hasPrimaryLocation W29138125561 @default.
- W2913812556 hasRelatedWork W1950940422 @default.
- W2913812556 hasRelatedWork W2032507829 @default.
- W2913812556 hasRelatedWork W2060210989 @default.
- W2913812556 hasRelatedWork W2129146436 @default.
- W2913812556 hasRelatedWork W2159052453 @default.
- W2913812556 hasRelatedWork W2566616303 @default.
- W2913812556 hasRelatedWork W2752972570 @default.
- W2913812556 hasRelatedWork W3013693939 @default.
- W2913812556 hasRelatedWork W3131327266 @default.
- W2913812556 hasRelatedWork W4283822356 @default.
- W2913812556 hasVolume "7" @default.
- W2913812556 isParatext "false" @default.