Matches in SemOpenAlex for { <https://semopenalex.org/work/W2553683256> ?p ?o ?g. }
- W2553683256 abstract "As an unsupervised learning method, sparse coding can discover high-level representations for an input in a large variety of learning problems. Under semi-supervised settings, sparse coding is used to extract features for a supervised task such as classification. While sparse representations learned from unlabeled data independently of the supervised task perform well, we argue that sparse coding should also be built as a holistic learning unit optimizing on the supervised task objectives more explicitly. In this paper, we propose sparse-coded net, a feedforward model that integrates sparse coding and task-driven output layers, and describe training methods in detail. After pretraining a sparse-coded net via semi-supervised learning, we optimize its task-specific performance in a novel backpropagation algorithm that can traverse nonlinear feature pooling operators to update the dictionary. Thus, sparse-coded net can be applied to supervised dictionary learning. We evaluate sparse-coded net with classification problems in sound, image, and text data. The results confirm a significant improvement over semi-supervised learning as well as superior classification performance against deep stacked autoencoder neural network and GMM-SVM pipelines in small to medium-scale settings." @default.
- W2553683256 created "2016-11-30" @default.
- W2553683256 creator A5012323997 @default.
- W2553683256 creator A5026993630 @default.
- W2553683256 creator A5029707299 @default.
- W2553683256 creator A5061064027 @default.
- W2553683256 creator A5066867900 @default.
- W2553683256 date "2016-09-01" @default.
- W2553683256 modified "2023-09-23" @default.
- W2553683256 title "Sparse-coded net model and applications" @default.
- W2553683256 cites W1985133440 @default.
- W2553683256 cites W2005876975 @default.
- W2553683256 cites W2012914973 @default.
- W2553683256 cites W2063978378 @default.
- W2553683256 cites W2086384421 @default.
- W2553683256 cites W2105464873 @default.
- W2553683256 cites W2106277773 @default.
- W2553683256 cites W2115549875 @default.
- W2553683256 cites W2118858186 @default.
- W2553683256 cites W2128659236 @default.
- W2553683256 cites W2135046866 @default.
- W2553683256 cites W2136922672 @default.
- W2553683256 cites W2145094598 @default.
- W2553683256 cites W2153635508 @default.
- W2553683256 cites W2160547390 @default.
- W2553683256 cites W2213844264 @default.
- W2553683256 cites W2402967400 @default.
- W2553683256 cites W2517097820 @default.
- W2553683256 cites W3118608800 @default.
- W2553683256 doi "https://doi.org/10.1109/mlsp.2016.7738828" @default.
- W2553683256 hasPublicationYear "2016" @default.
- W2553683256 type Work @default.
- W2553683256 sameAs 2553683256 @default.
- W2553683256 citedByCount "0" @default.
- W2553683256 crossrefType "proceedings-article" @default.
- W2553683256 hasAuthorship W2553683256A5012323997 @default.
- W2553683256 hasAuthorship W2553683256A5026993630 @default.
- W2553683256 hasAuthorship W2553683256A5029707299 @default.
- W2553683256 hasAuthorship W2553683256A5061064027 @default.
- W2553683256 hasAuthorship W2553683256A5066867900 @default.
- W2553683256 hasConcept C101738243 @default.
- W2553683256 hasConcept C108583219 @default.
- W2553683256 hasConcept C119857082 @default.
- W2553683256 hasConcept C121332964 @default.
- W2553683256 hasConcept C124066611 @default.
- W2553683256 hasConcept C136389625 @default.
- W2553683256 hasConcept C153180895 @default.
- W2553683256 hasConcept C154945302 @default.
- W2553683256 hasConcept C155032097 @default.
- W2553683256 hasConcept C163716315 @default.
- W2553683256 hasConcept C41008148 @default.
- W2553683256 hasConcept C50644808 @default.
- W2553683256 hasConcept C56372850 @default.
- W2553683256 hasConcept C57273362 @default.
- W2553683256 hasConcept C58973888 @default.
- W2553683256 hasConcept C62520636 @default.
- W2553683256 hasConcept C76155785 @default.
- W2553683256 hasConcept C77637269 @default.
- W2553683256 hasConcept C8038995 @default.
- W2553683256 hasConceptScore W2553683256C101738243 @default.
- W2553683256 hasConceptScore W2553683256C108583219 @default.
- W2553683256 hasConceptScore W2553683256C119857082 @default.
- W2553683256 hasConceptScore W2553683256C121332964 @default.
- W2553683256 hasConceptScore W2553683256C124066611 @default.
- W2553683256 hasConceptScore W2553683256C136389625 @default.
- W2553683256 hasConceptScore W2553683256C153180895 @default.
- W2553683256 hasConceptScore W2553683256C154945302 @default.
- W2553683256 hasConceptScore W2553683256C155032097 @default.
- W2553683256 hasConceptScore W2553683256C163716315 @default.
- W2553683256 hasConceptScore W2553683256C41008148 @default.
- W2553683256 hasConceptScore W2553683256C50644808 @default.
- W2553683256 hasConceptScore W2553683256C56372850 @default.
- W2553683256 hasConceptScore W2553683256C57273362 @default.
- W2553683256 hasConceptScore W2553683256C58973888 @default.
- W2553683256 hasConceptScore W2553683256C62520636 @default.
- W2553683256 hasConceptScore W2553683256C76155785 @default.
- W2553683256 hasConceptScore W2553683256C77637269 @default.
- W2553683256 hasConceptScore W2553683256C8038995 @default.
- W2553683256 hasLocation W25536832561 @default.
- W2553683256 hasOpenAccess W2553683256 @default.
- W2553683256 hasPrimaryLocation W25536832561 @default.
- W2553683256 hasRelatedWork W1486698398 @default.
- W2553683256 hasRelatedWork W1492130155 @default.
- W2553683256 hasRelatedWork W1969972839 @default.
- W2553683256 hasRelatedWork W2022673988 @default.
- W2553683256 hasRelatedWork W2118834604 @default.
- W2553683256 hasRelatedWork W2145376937 @default.
- W2553683256 hasRelatedWork W2156671090 @default.
- W2553683256 hasRelatedWork W2242427765 @default.
- W2553683256 hasRelatedWork W2467064228 @default.
- W2553683256 hasRelatedWork W2524861486 @default.
- W2553683256 hasRelatedWork W2561508064 @default.
- W2553683256 hasRelatedWork W2736499595 @default.
- W2553683256 hasRelatedWork W2890954125 @default.
- W2553683256 hasRelatedWork W2953042074 @default.
- W2553683256 hasRelatedWork W2962744053 @default.
- W2553683256 hasRelatedWork W3086580107 @default.
- W2553683256 hasRelatedWork W3168606595 @default.
- W2553683256 hasRelatedWork W3176624929 @default.
- W2553683256 hasRelatedWork W3204104158 @default.