Matches in SemOpenAlex for { <https://semopenalex.org/work/W1991859098> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W1991859098 abstract "To achieve high performance in object recognition, a high-level feature representation is play an essential role to transform a raw input data (low-level) into a new representation. Unsupervised feature learning is one of the most successful methods that is widely used in machine learning literatures for creating a high-level feature to improve the supervised learning problems. The main concept of unsupervised feature learning is, in some sense, to encode input knowledge for gaining not only latent features but compact high-fidelity representation. In particular, a sparse coding has proven to be an effective tool as a prior lead to state-of-the-art performance in many benchmark datasets. In sparse coding, an input data can be represented as a sparse linear combination of a set of training overcomplete dictionary. However, an open problem in sparse coding is how to create and correctly choose the dictionary for representing a given input. Moreover, some bases of the learned dictionary is highly dependent and non-orthogonal among itself. In this study, we propose a post-processing scheme to transform the overcomplete dictionary obtained from unsupervised feature learning using Principle Component Analysis (PCA). The goal of our post-processing is to reduce the number of bases in the unsupervised dictionary learning for real-time applications. In experimental results, while the performance without post-processing the unsupervised dictionary learning is better than that of using PCA, it takes more computation and requires more resources during the test time." @default.
- W1991859098 created "2016-06-24" @default.
- W1991859098 creator A5053768680 @default.
- W1991859098 creator A5060504511 @default.
- W1991859098 date "2014-09-01" @default.
- W1991859098 modified "2023-09-27" @default.
- W1991859098 title "Post-processing of unsupervised dictionary learning in handwritten digit recognition" @default.
- W1991859098 cites W1965555277 @default.
- W1991859098 cites W1989975849 @default.
- W1991859098 cites W2005876975 @default.
- W1991859098 cites W2100495367 @default.
- W1991859098 cites W2105464873 @default.
- W1991859098 cites W2110798204 @default.
- W1991859098 cites W2122922389 @default.
- W1991859098 cites W2124537004 @default.
- W1991859098 cites W2129812935 @default.
- W1991859098 cites W2145889472 @default.
- W1991859098 cites W2149684865 @default.
- W1991859098 cites W2151693816 @default.
- W1991859098 cites W2253807446 @default.
- W1991859098 cites W34239198 @default.
- W1991859098 doi "https://doi.org/10.1109/iscit.2014.7011893" @default.
- W1991859098 hasPublicationYear "2014" @default.
- W1991859098 type Work @default.
- W1991859098 sameAs 1991859098 @default.
- W1991859098 citedByCount "0" @default.
- W1991859098 crossrefType "proceedings-article" @default.
- W1991859098 hasAuthorship W1991859098A5053768680 @default.
- W1991859098 hasAuthorship W1991859098A5060504511 @default.
- W1991859098 hasConcept C119857082 @default.
- W1991859098 hasConcept C124066611 @default.
- W1991859098 hasConcept C138885662 @default.
- W1991859098 hasConcept C153180895 @default.
- W1991859098 hasConcept C154771677 @default.
- W1991859098 hasConcept C154945302 @default.
- W1991859098 hasConcept C2776401178 @default.
- W1991859098 hasConcept C41008148 @default.
- W1991859098 hasConcept C41895202 @default.
- W1991859098 hasConcept C59404180 @default.
- W1991859098 hasConcept C77637269 @default.
- W1991859098 hasConcept C8038995 @default.
- W1991859098 hasConceptScore W1991859098C119857082 @default.
- W1991859098 hasConceptScore W1991859098C124066611 @default.
- W1991859098 hasConceptScore W1991859098C138885662 @default.
- W1991859098 hasConceptScore W1991859098C153180895 @default.
- W1991859098 hasConceptScore W1991859098C154771677 @default.
- W1991859098 hasConceptScore W1991859098C154945302 @default.
- W1991859098 hasConceptScore W1991859098C2776401178 @default.
- W1991859098 hasConceptScore W1991859098C41008148 @default.
- W1991859098 hasConceptScore W1991859098C41895202 @default.
- W1991859098 hasConceptScore W1991859098C59404180 @default.
- W1991859098 hasConceptScore W1991859098C77637269 @default.
- W1991859098 hasConceptScore W1991859098C8038995 @default.
- W1991859098 hasLocation W19918590981 @default.
- W1991859098 hasOpenAccess W1991859098 @default.
- W1991859098 hasPrimaryLocation W19918590981 @default.
- W1991859098 hasRelatedWork W1021103032 @default.
- W1991859098 hasRelatedWork W1581016441 @default.
- W1991859098 hasRelatedWork W1987645143 @default.
- W1991859098 hasRelatedWork W2056380775 @default.
- W1991859098 hasRelatedWork W2064605643 @default.
- W1991859098 hasRelatedWork W2108665656 @default.
- W1991859098 hasRelatedWork W2142873256 @default.
- W1991859098 hasRelatedWork W2164835629 @default.
- W1991859098 hasRelatedWork W2301105015 @default.
- W1991859098 hasRelatedWork W2525624297 @default.
- W1991859098 hasRelatedWork W2553768359 @default.
- W1991859098 hasRelatedWork W2604913466 @default.
- W1991859098 hasRelatedWork W2781836892 @default.
- W1991859098 hasRelatedWork W2953139536 @default.
- W1991859098 hasRelatedWork W2955328952 @default.
- W1991859098 hasRelatedWork W2995624411 @default.
- W1991859098 hasRelatedWork W3000032785 @default.
- W1991859098 hasRelatedWork W3005273389 @default.
- W1991859098 hasRelatedWork W3066608393 @default.
- W1991859098 hasRelatedWork W91719414 @default.
- W1991859098 isParatext "false" @default.
- W1991859098 isRetracted "false" @default.
- W1991859098 magId "1991859098" @default.
- W1991859098 workType "article" @default.