FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090026837> ?p ?o ?g. }

• W3090026837 endingPage "241" @default.
• W3090026837 startingPage "217" @default.
• W3090026837 abstract "We propose an alternative to the generative classifier that usually models both the class conditionals and class priors separately, and then uses the Bayes theorem to compute the posterior distribution of classes given the training set as a decision boundary. Because SVM (support vector machine) is not a probabilistic framework, it is really difficult to implement a direct posterior distribution-based discriminative classifier. As SVM lacks in full Bayesian analysis, we propose a hybrid (generative–discriminative) technique where the generative topic features from a Bayesian learning are fed to the SVM. The standard latent Dirichlet allocation topic model with its Dirichlet (Dir) prior could be defined as Dir–Dir topic model to characterize the Dirichlet placed on the document and corpus parameters. With very flexible conjugate priors to the multinomials such as generalized Dirichlet (GD) and Beta-Liouville (BL) in our proposed approach, we define two new topic models: the BL–GD and GD–BL. We take advantage of the geometric interpretation of our generative topic (latent) models that associate a K-dimensional manifold (K is the size of the topics) embedded into a V-dimensional feature space (word simplex) where V is the vocabulary size. Under this structure, the low-dimensional topic simplex (the subspace) defines a document as a single point on its manifold and associates each document with a single probability. The SVM, with its kernel trick, performs on these document probabilities in classification where it utilizes the maximum margin learning approach as a decision boundary. The key note is that points or documents that are close to each other on the manifold must belong to the same class. Experimental results with text documents and images show the merits of the proposed framework." @default.
• W3090026837 created "2020-10-08" @default.
• W3090026837 creator A5000251216 @default.
• W3090026837 creator A5065896848 @default.
• W3090026837 creator A5090600716 @default.
• W3090026837 date "2020-09-30" @default.
• W3090026837 modified "2023-10-03" @default.
• W3090026837 title "Efficient integration of generative topic models into discriminative classifiers using robust probabilistic kernels" @default.
• W3090026837 cites W114980831 @default.
• W3090026837 cites W1574979081 @default.
• W3090026837 cites W1596052433 @default.
• W3090026837 cites W1783453637 @default.
• W3090026837 cites W1828567212 @default.
• W3090026837 cites W1969486090 @default.
• W3090026837 cites W1985367615 @default.
• W3090026837 cites W2000930721 @default.
• W3090026837 cites W2001975024 @default.
• W3090026837 cites W2005181355 @default.
• W3090026837 cites W2022149269 @default.
• W3090026837 cites W2030922352 @default.
• W3090026837 cites W2037090920 @default.
• W3090026837 cites W2055337076 @default.
• W3090026837 cites W2067802667 @default.
• W3090026837 cites W2072644219 @default.
• W3090026837 cites W2098663280 @default.
• W3090026837 cites W2099090453 @default.
• W3090026837 cites W2103658758 @default.
• W3090026837 cites W2106490775 @default.
• W3090026837 cites W2106868411 @default.
• W3090026837 cites W2107034620 @default.
• W3090026837 cites W2109868644 @default.
• W3090026837 cites W2110642088 @default.
• W3090026837 cites W2111861094 @default.
• W3090026837 cites W2121915926 @default.
• W3090026837 cites W2130428211 @default.
• W3090026837 cites W2143869282 @default.
• W3090026837 cites W2144100511 @default.
• W3090026837 cites W2144245426 @default.
• W3090026837 cites W2146950091 @default.
• W3090026837 cites W2152594362 @default.
• W3090026837 cites W2154422044 @default.
• W3090026837 cites W2158266063 @default.
• W3090026837 cites W2160360539 @default.
• W3090026837 cites W2162915993 @default.
• W3090026837 cites W2163679724 @default.
• W3090026837 cites W2167828171 @default.
• W3090026837 cites W2170902875 @default.
• W3090026837 cites W2172191903 @default.
• W3090026837 cites W2255966421 @default.
• W3090026837 cites W2287233148 @default.
• W3090026837 cites W2464651140 @default.
• W3090026837 cites W2527995191 @default.
• W3090026837 cites W2551838879 @default.
• W3090026837 cites W2740139069 @default.
• W3090026837 cites W2750981579 @default.
• W3090026837 cites W2785337891 @default.
• W3090026837 cites W2789871865 @default.
• W3090026837 cites W2792763200 @default.
• W3090026837 cites W2794720137 @default.
• W3090026837 cites W2798798513 @default.
• W3090026837 cites W2808040408 @default.
• W3090026837 cites W2883186795 @default.
• W3090026837 cites W2888631542 @default.
• W3090026837 cites W2890842057 @default.
• W3090026837 cites W2895163674 @default.
• W3090026837 cites W2907966865 @default.
• W3090026837 cites W2911250003 @default.
• W3090026837 cites W2947220628 @default.
• W3090026837 cites W2955851689 @default.
• W3090026837 cites W2962943175 @default.
• W3090026837 cites W2963034284 @default.
• W3090026837 cites W2963319967 @default.
• W3090026837 cites W2974249822 @default.
• W3090026837 cites W2987710261 @default.
• W3090026837 cites W2990140544 @default.
• W3090026837 cites W4233135949 @default.
• W3090026837 doi "https://doi.org/10.1007/s10044-020-00917-1" @default.
• W3090026837 hasPublicationYear "2020" @default.
• W3090026837 type Work @default.
• W3090026837 sameAs 3090026837 @default.
• W3090026837 citedByCount "2" @default.
• W3090026837 countsByYear W30900268372022 @default.
• W3090026837 countsByYear W30900268372023 @default.
• W3090026837 crossrefType "journal-article" @default.
• W3090026837 hasAuthorship W3090026837A5000251216 @default.
• W3090026837 hasAuthorship W3090026837A5065896848 @default.
• W3090026837 hasAuthorship W3090026837A5090600716 @default.
• W3090026837 hasBestOaLocation W30900268372 @default.
• W3090026837 hasConcept C107673813 @default.
• W3090026837 hasConcept C119857082 @default.
• W3090026837 hasConcept C12267149 @default.
• W3090026837 hasConcept C134306372 @default.
• W3090026837 hasConcept C153180895 @default.
• W3090026837 hasConcept C154945302 @default.
• W3090026837 hasConcept C167966045 @default.
• W3090026837 hasConcept C169214877 @default.
• W3090026837 hasConcept C171686336 @default.
• W3090026837 hasConcept C177769412 @default.

• next