Matches in SemOpenAlex for { <https://semopenalex.org/work/W2065652296> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2065652296 endingPage "1450034" @default.
- W2065652296 startingPage "1450034" @default.
- W2065652296 abstract "There is an increasing interest in the machine learning community to automatically learn feature representations directly from the (unlabeled) data instead of using hand-designed features. The autoencoder is one method that can be used for this purpose. However, for data sets with a high degree of noise, a large amount of the representational capacity in the autoencoder is used to minimize the reconstruction error for these noisy inputs. This paper proposes a method that improves the feature learning process by focusing on the task relevant information in the data. This selective attention is achieved by weighting the reconstruction error and reducing the influence of noisy inputs during the learning process. The proposed model is trained on a number of publicly available image data sets and the test error rate is compared to a standard sparse autoencoder and other methods, such as the denoising autoencoder and contractive autoencoder." @default.
- W2065652296 created "2016-06-24" @default.
- W2065652296 creator A5025841244 @default.
- W2065652296 creator A5065061690 @default.
- W2065652296 date "2015-01-06" @default.
- W2065652296 modified "2023-09-25" @default.
- W2065652296 title "Learning Feature Representations with a Cost-Relevant Sparse Autoencoder" @default.
- W2065652296 cites W1806891645 @default.
- W2065652296 cites W1999720027 @default.
- W2065652296 cites W2026942141 @default.
- W2065652296 cites W2057853719 @default.
- W2065652296 cites W2098874108 @default.
- W2065652296 cites W2100495367 @default.
- W2065652296 cites W2118978333 @default.
- W2065652296 cites W2136922672 @default.
- W2065652296 cites W2163922914 @default.
- W2065652296 cites W4231109964 @default.
- W2065652296 doi "https://doi.org/10.1142/s0129065714500348" @default.
- W2065652296 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/25515941" @default.
- W2065652296 hasPublicationYear "2015" @default.
- W2065652296 type Work @default.
- W2065652296 sameAs 2065652296 @default.
- W2065652296 citedByCount "18" @default.
- W2065652296 countsByYear W20656522962016 @default.
- W2065652296 countsByYear W20656522962017 @default.
- W2065652296 countsByYear W20656522962018 @default.
- W2065652296 countsByYear W20656522962019 @default.
- W2065652296 countsByYear W20656522962020 @default.
- W2065652296 countsByYear W20656522962021 @default.
- W2065652296 countsByYear W20656522962022 @default.
- W2065652296 countsByYear W20656522962023 @default.
- W2065652296 crossrefType "journal-article" @default.
- W2065652296 hasAuthorship W2065652296A5025841244 @default.
- W2065652296 hasAuthorship W2065652296A5065061690 @default.
- W2065652296 hasConcept C101738243 @default.
- W2065652296 hasConcept C108583219 @default.
- W2065652296 hasConcept C111919701 @default.
- W2065652296 hasConcept C115961682 @default.
- W2065652296 hasConcept C119857082 @default.
- W2065652296 hasConcept C126838900 @default.
- W2065652296 hasConcept C138885662 @default.
- W2065652296 hasConcept C153180895 @default.
- W2065652296 hasConcept C154945302 @default.
- W2065652296 hasConcept C162324750 @default.
- W2065652296 hasConcept C183115368 @default.
- W2065652296 hasConcept C187736073 @default.
- W2065652296 hasConcept C2776401178 @default.
- W2065652296 hasConcept C2780451532 @default.
- W2065652296 hasConcept C40969351 @default.
- W2065652296 hasConcept C41008148 @default.
- W2065652296 hasConcept C41895202 @default.
- W2065652296 hasConcept C59404180 @default.
- W2065652296 hasConcept C71924100 @default.
- W2065652296 hasConcept C98045186 @default.
- W2065652296 hasConcept C99498987 @default.
- W2065652296 hasConceptScore W2065652296C101738243 @default.
- W2065652296 hasConceptScore W2065652296C108583219 @default.
- W2065652296 hasConceptScore W2065652296C111919701 @default.
- W2065652296 hasConceptScore W2065652296C115961682 @default.
- W2065652296 hasConceptScore W2065652296C119857082 @default.
- W2065652296 hasConceptScore W2065652296C126838900 @default.
- W2065652296 hasConceptScore W2065652296C138885662 @default.
- W2065652296 hasConceptScore W2065652296C153180895 @default.
- W2065652296 hasConceptScore W2065652296C154945302 @default.
- W2065652296 hasConceptScore W2065652296C162324750 @default.
- W2065652296 hasConceptScore W2065652296C183115368 @default.
- W2065652296 hasConceptScore W2065652296C187736073 @default.
- W2065652296 hasConceptScore W2065652296C2776401178 @default.
- W2065652296 hasConceptScore W2065652296C2780451532 @default.
- W2065652296 hasConceptScore W2065652296C40969351 @default.
- W2065652296 hasConceptScore W2065652296C41008148 @default.
- W2065652296 hasConceptScore W2065652296C41895202 @default.
- W2065652296 hasConceptScore W2065652296C59404180 @default.
- W2065652296 hasConceptScore W2065652296C71924100 @default.
- W2065652296 hasConceptScore W2065652296C98045186 @default.
- W2065652296 hasConceptScore W2065652296C99498987 @default.
- W2065652296 hasIssue "01" @default.
- W2065652296 hasLocation W20656522961 @default.
- W2065652296 hasLocation W20656522962 @default.
- W2065652296 hasOpenAccess W2065652296 @default.
- W2065652296 hasPrimaryLocation W20656522961 @default.
- W2065652296 hasRelatedWork W2292254049 @default.
- W2065652296 hasRelatedWork W2530216401 @default.
- W2065652296 hasRelatedWork W2546942002 @default.
- W2065652296 hasRelatedWork W2592385986 @default.
- W2065652296 hasRelatedWork W2998168123 @default.
- W2065652296 hasRelatedWork W3118590274 @default.
- W2065652296 hasRelatedWork W3165463024 @default.
- W2065652296 hasRelatedWork W3169547290 @default.
- W2065652296 hasRelatedWork W4287178339 @default.
- W2065652296 hasRelatedWork W4287995534 @default.
- W2065652296 hasVolume "25" @default.
- W2065652296 isParatext "false" @default.
- W2065652296 isRetracted "false" @default.
- W2065652296 magId "2065652296" @default.
- W2065652296 workType "article" @default.