Matches in SemOpenAlex for { <https://semopenalex.org/work/W2555072419> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W2555072419 abstract "This work proposes to learn autoencoders with sparse connections. Prior studies on autoencoders enforced sparsity on the neuronal activity; these are different from our proposed approach - we learn sparse connections. Sparsity in connections helps in learning (and keeping) the important relations while trimming the irrelevant ones. We have tested the performance of our proposed method on two tasks - classification and denoising. For classification we have compared against stacked autneencoders, contractive autoencoders, deep belief network, sparse deep neural network and optimal brain damage neural network; the denoising performance was compared against denoising autoencoder and sparse (activity) autoencoder. In both the tasks our proposed method yields superior results." @default.
- W2555072419 created "2016-11-30" @default.
- W2555072419 creator A5020310463 @default.
- W2555072419 creator A5035333894 @default.
- W2555072419 date "2016-07-01" @default.
- W2555072419 modified "2023-09-27" @default.
- W2555072419 title "Sparsely connected autoencoder" @default.
- W2555072419 cites W1206692776 @default.
- W2555072419 cites W1659448245 @default.
- W2555072419 cites W1964155876 @default.
- W2555072419 cites W1980454827 @default.
- W2555072419 cites W2004227461 @default.
- W2555072419 cites W2022449488 @default.
- W2555072419 cites W2028781966 @default.
- W2555072419 cites W2112984492 @default.
- W2555072419 cites W2121160181 @default.
- W2555072419 cites W2127271355 @default.
- W2555072419 cites W2128659236 @default.
- W2555072419 cites W2129638195 @default.
- W2555072419 cites W2129812935 @default.
- W2555072419 cites W2133665775 @default.
- W2555072419 cites W2133824856 @default.
- W2555072419 cites W2166537789 @default.
- W2555072419 cites W4250955649 @default.
- W2555072419 doi "https://doi.org/10.1109/ijcnn.2016.7727437" @default.
- W2555072419 hasPublicationYear "2016" @default.
- W2555072419 type Work @default.
- W2555072419 sameAs 2555072419 @default.
- W2555072419 citedByCount "4" @default.
- W2555072419 countsByYear W25550724192017 @default.
- W2555072419 countsByYear W25550724192018 @default.
- W2555072419 countsByYear W25550724192019 @default.
- W2555072419 crossrefType "proceedings-article" @default.
- W2555072419 hasAuthorship W2555072419A5020310463 @default.
- W2555072419 hasAuthorship W2555072419A5035333894 @default.
- W2555072419 hasConcept C101738243 @default.
- W2555072419 hasConcept C154945302 @default.
- W2555072419 hasConcept C41008148 @default.
- W2555072419 hasConcept C50644808 @default.
- W2555072419 hasConceptScore W2555072419C101738243 @default.
- W2555072419 hasConceptScore W2555072419C154945302 @default.
- W2555072419 hasConceptScore W2555072419C41008148 @default.
- W2555072419 hasConceptScore W2555072419C50644808 @default.
- W2555072419 hasLocation W25550724191 @default.
- W2555072419 hasOpenAccess W2555072419 @default.
- W2555072419 hasPrimaryLocation W25550724191 @default.
- W2555072419 hasRelatedWork W2283340597 @default.
- W2555072419 hasRelatedWork W2589098947 @default.
- W2555072419 hasRelatedWork W2748952813 @default.
- W2555072419 hasRelatedWork W2785529134 @default.
- W2555072419 hasRelatedWork W2899084033 @default.
- W2555072419 hasRelatedWork W2927931735 @default.
- W2555072419 hasRelatedWork W2946739205 @default.
- W2555072419 hasRelatedWork W3019797369 @default.
- W2555072419 hasRelatedWork W3048468193 @default.
- W2555072419 hasRelatedWork W3085258535 @default.
- W2555072419 isParatext "false" @default.
- W2555072419 isRetracted "false" @default.
- W2555072419 magId "2555072419" @default.
- W2555072419 workType "article" @default.