FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2978758977> ?p ?o ?g. }

• W2978758977 abstract "This work introduces certain supervised formulations for transform learning. Transform learning is the analysis equivalent of dictionary learning. Four different types of supervision penalties are proposed. The first one is class-sparsity, which imposes common sparse support within representations of each class. The second one imposes similarity among intra-class features in terms of a low-rank constraint (high cosine similarity). The third penalty enforces features of the same class to be nearby each other and features of different classes to be far apart. The final formulation is the well known label-consistency formulation which learns a linear map from the feature space to the class targets. For the first time, we show how transform learning (and its supervised versions can be kernelized). Finally this work also introduces stochastic regularization techniques like DropOut and DropConnect into the transform learning formulation. Experiments have been carried out on two different problems – computer vision and biomedial signal analysis. In both the problems, our method excels over all existing ones." @default.
• W2978758977 created "2019-10-10" @default.
• W2978758977 creator A5020310463 @default.
• W2978758977 creator A5061490660 @default.
• W2978758977 date "2019-07-01" @default.
• W2978758977 modified "2023-09-25" @default.
• W2978758977 title "Supervised Kernel Transform Learning" @default.
• W2978758977 cites W1902027874 @default.
• W2978758977 cites W1927762903 @default.
• W2978758977 cites W1979646128 @default.
• W2978758977 cites W1986611834 @default.
• W2978758977 cites W1989833002 @default.
• W2978758977 cites W1994281301 @default.
• W2978758977 cites W2002932002 @default.
• W2978758977 cites W2011464887 @default.
• W2978758977 cites W2027805700 @default.
• W2978758977 cites W2077964948 @default.
• W2978758977 cites W2093238275 @default.
• W2978758977 cites W2097200430 @default.
• W2978758977 cites W2099321050 @default.
• W2978758977 cites W2115429828 @default.
• W2978758977 cites W2115706991 @default.
• W2978758977 cites W2117882039 @default.
• W2978758977 cites W2118057659 @default.
• W2978758977 cites W2141039087 @default.
• W2978758977 cites W2146842127 @default.
• W2978758977 cites W2149861038 @default.
• W2978758977 cites W2153663612 @default.
• W2978758977 cites W2154672679 @default.
• W2978758977 cites W2160547390 @default.
• W2978758977 cites W2163112044 @default.
• W2978758977 cites W2163398148 @default.
• W2978758977 cites W2254969944 @default.
• W2978758977 cites W2289846183 @default.
• W2978758977 cites W2291961022 @default.
• W2978758977 cites W2330290358 @default.
• W2978758977 cites W2343962831 @default.
• W2978758977 cites W2390063609 @default.
• W2978758977 cites W2547190925 @default.
• W2978758977 cites W2753163043 @default.
• W2978758977 cites W2754803257 @default.
• W2978758977 cites W2963958000 @default.
• W2978758977 cites W3100063120 @default.
• W2978758977 cites W4919037 @default.
• W2978758977 doi "https://doi.org/10.1109/ijcnn.2019.8852179" @default.
• W2978758977 hasPublicationYear "2019" @default.
• W2978758977 type Work @default.
• W2978758977 sameAs 2978758977 @default.
• W2978758977 citedByCount "2" @default.
• W2978758977 countsByYear W29787589772021 @default.
• W2978758977 countsByYear W29787589772023 @default.
• W2978758977 crossrefType "proceedings-article" @default.
• W2978758977 hasAuthorship W2978758977A5020310463 @default.
• W2978758977 hasAuthorship W2978758977A5061490660 @default.
• W2978758977 hasConcept C103278499 @default.
• W2978758977 hasConcept C114614502 @default.
• W2978758977 hasConcept C115961682 @default.
• W2978758977 hasConcept C119857082 @default.
• W2978758977 hasConcept C138885662 @default.
• W2978758977 hasConcept C153180895 @default.
• W2978758977 hasConcept C154945302 @default.
• W2978758977 hasConcept C2221639 @default.
• W2978758977 hasConcept C2776135515 @default.
• W2978758977 hasConcept C2776401178 @default.
• W2978758977 hasConcept C2777212361 @default.
• W2978758977 hasConcept C33923547 @default.
• W2978758977 hasConcept C41008148 @default.
• W2978758977 hasConcept C41895202 @default.
• W2978758977 hasConcept C74193536 @default.
• W2978758977 hasConcept C83665646 @default.
• W2978758977 hasConceptScore W2978758977C103278499 @default.
• W2978758977 hasConceptScore W2978758977C114614502 @default.
• W2978758977 hasConceptScore W2978758977C115961682 @default.
• W2978758977 hasConceptScore W2978758977C119857082 @default.
• W2978758977 hasConceptScore W2978758977C138885662 @default.
• W2978758977 hasConceptScore W2978758977C153180895 @default.
• W2978758977 hasConceptScore W2978758977C154945302 @default.
• W2978758977 hasConceptScore W2978758977C2221639 @default.
• W2978758977 hasConceptScore W2978758977C2776135515 @default.
• W2978758977 hasConceptScore W2978758977C2776401178 @default.
• W2978758977 hasConceptScore W2978758977C2777212361 @default.
• W2978758977 hasConceptScore W2978758977C33923547 @default.
• W2978758977 hasConceptScore W2978758977C41008148 @default.
• W2978758977 hasConceptScore W2978758977C41895202 @default.
• W2978758977 hasConceptScore W2978758977C74193536 @default.
• W2978758977 hasConceptScore W2978758977C83665646 @default.
• W2978758977 hasLocation W29787589771 @default.
• W2978758977 hasOpenAccess W2978758977 @default.
• W2978758977 hasPrimaryLocation W29787589771 @default.
• W2978758977 hasRelatedWork W2122007323 @default.
• W2978758977 hasRelatedWork W2593752079 @default.
• W2978758977 hasRelatedWork W2594455805 @default.
• W2978758977 hasRelatedWork W2615416810 @default.
• W2978758977 hasRelatedWork W2741121443 @default.
• W2978758977 hasRelatedWork W2743316710 @default.
• W2978758977 hasRelatedWork W2761584071 @default.
• W2978758977 hasRelatedWork W2890747888 @default.
• W2978758977 hasRelatedWork W2896313677 @default.
• W2978758977 hasRelatedWork W2912465789 @default.
• W2978758977 hasRelatedWork W2927010241 @default.

• next