Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987652334> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2987652334 abstract "State-of-the-art pattern recognition methods have difficulties dealing with problems where the dimension of the output space is large. In this article, we propose a framework based on deep architectures (e.g. Deep Neural Networks) in order to deal with this issue. Deep architectures have proven to be efficient for high dimensional input problems such as image classification, due to their ability to embed the input space. The main contribution of this article is the extension of the embedding procedure to both the input and output spaces to easily handle complex outputs. Using this extension, inter- output dependencies can be modelled efficiently. This provides an interesting alternative to probabilistic models such as HMM and CRF. Preliminary experiments on toy datasets and USPS character reconstruction show promising results. Keywords-High dimensional output, Neural Networks, Image Segmentation" @default.
- W2987652334 created "2019-11-22" @default.
- W2987652334 creator A5037122730 @default.
- W2987652334 date "2009-01-01" @default.
- W2987652334 modified "2023-09-26" @default.
- W2987652334 title "Learning Deep Neural Networks for High Dimensional Output Problems" @default.
- W2987652334 cites W1525954826 @default.
- W2987652334 cites W1554544485 @default.
- W2987652334 cites W2074392786 @default.
- W2987652334 cites W2097581247 @default.
- W2987652334 cites W2103194807 @default.
- W2987652334 cites W2110798204 @default.
- W2987652334 cites W2125838338 @default.
- W2987652334 cites W2136922672 @default.
- W2987652334 cites W2140833774 @default.
- W2987652334 cites W2146156528 @default.
- W2987652334 cites W2158619730 @default.
- W2987652334 cites W2159291644 @default.
- W2987652334 cites W2799061466 @default.
- W2987652334 hasPublicationYear "2009" @default.
- W2987652334 type Work @default.
- W2987652334 sameAs 2987652334 @default.
- W2987652334 citedByCount "0" @default.
- W2987652334 crossrefType "journal-article" @default.
- W2987652334 hasAuthorship W2987652334A5037122730 @default.
- W2987652334 hasConcept C108583219 @default.
- W2987652334 hasConcept C115961682 @default.
- W2987652334 hasConcept C153180895 @default.
- W2987652334 hasConcept C154945302 @default.
- W2987652334 hasConcept C199360897 @default.
- W2987652334 hasConcept C202444582 @default.
- W2987652334 hasConcept C2778029271 @default.
- W2987652334 hasConcept C2984842247 @default.
- W2987652334 hasConcept C33676613 @default.
- W2987652334 hasConcept C33923547 @default.
- W2987652334 hasConcept C41008148 @default.
- W2987652334 hasConcept C41608201 @default.
- W2987652334 hasConcept C50644808 @default.
- W2987652334 hasConcept C89600930 @default.
- W2987652334 hasConceptScore W2987652334C108583219 @default.
- W2987652334 hasConceptScore W2987652334C115961682 @default.
- W2987652334 hasConceptScore W2987652334C153180895 @default.
- W2987652334 hasConceptScore W2987652334C154945302 @default.
- W2987652334 hasConceptScore W2987652334C199360897 @default.
- W2987652334 hasConceptScore W2987652334C202444582 @default.
- W2987652334 hasConceptScore W2987652334C2778029271 @default.
- W2987652334 hasConceptScore W2987652334C2984842247 @default.
- W2987652334 hasConceptScore W2987652334C33676613 @default.
- W2987652334 hasConceptScore W2987652334C33923547 @default.
- W2987652334 hasConceptScore W2987652334C41008148 @default.
- W2987652334 hasConceptScore W2987652334C41608201 @default.
- W2987652334 hasConceptScore W2987652334C50644808 @default.
- W2987652334 hasConceptScore W2987652334C89600930 @default.
- W2987652334 hasLocation W29876523341 @default.
- W2987652334 hasOpenAccess W2987652334 @default.
- W2987652334 hasPrimaryLocation W29876523341 @default.
- W2987652334 hasRelatedWork W131647911 @default.
- W2987652334 hasRelatedWork W1542594606 @default.
- W2987652334 hasRelatedWork W2195388612 @default.
- W2987652334 hasRelatedWork W2468983453 @default.
- W2987652334 hasRelatedWork W2525954470 @default.
- W2987652334 hasRelatedWork W2587297661 @default.
- W2987652334 hasRelatedWork W2785373760 @default.
- W2987652334 hasRelatedWork W2902350839 @default.
- W2987652334 hasRelatedWork W2932454681 @default.
- W2987652334 hasRelatedWork W2955530511 @default.
- W2987652334 hasRelatedWork W2968898024 @default.
- W2987652334 hasRelatedWork W2971808011 @default.
- W2987652334 hasRelatedWork W2974790478 @default.
- W2987652334 hasRelatedWork W2995908305 @default.
- W2987652334 hasRelatedWork W2997992893 @default.
- W2987652334 hasRelatedWork W3012257539 @default.
- W2987652334 hasRelatedWork W3021121106 @default.
- W2987652334 hasRelatedWork W3164261842 @default.
- W2987652334 hasRelatedWork W3211097789 @default.
- W2987652334 hasRelatedWork W84607321 @default.
- W2987652334 isParatext "false" @default.
- W2987652334 isRetracted "false" @default.
- W2987652334 magId "2987652334" @default.
- W2987652334 workType "article" @default.