FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2419541780> ?p ?o ?g. }

• W2419541780 endingPage "1355" @default.
• W2419541780 startingPage "1347" @default.
• W2419541780 abstract "Belief networks are commonly used generative models of data, but require expensive posterior estimation to train and test the model. Learning typically proceeds by posterior sampling, variational approximations, or recognition networks, combined with stochastic optimization. We propose using an online Monte Carlo expectationmaximization (MCEM) algorithm to learn the maximum a posteriori (MAP) estimator of the generative model or optimize the variational lower bound of a recognition network. The E-step in this algorithm requires posterior samples, which are already generated in current learning schema. For the M-step, we augment with Polya-Gamma (PG) random variables to give an analytic updating scheme. We show relationships to standard learning approaches by deriving stochastic gradient ascent in the MCEM framework. We apply the proposed methods to both binary and count data. Experimental results show that MCEM improves the convergence speed and often improves hold-out performance over existing learning methods. Our approach is readily generalized to other recognition networks." @default.
• W2419541780 created "2016-06-24" @default.
• W2419541780 creator A5008391481 @default.
• W2419541780 creator A5016448581 @default.
• W2419541780 creator A5052576907 @default.
• W2419541780 creator A5056639842 @default.
• W2419541780 date "2016-05-02" @default.
• W2419541780 modified "2023-09-24" @default.
• W2419541780 title "Learning Sigmoid Belief Networks via Monte Carlo Expectation Maximization" @default.
• W2419541780 cites W1520448186 @default.
• W2419541780 cites W1525164363 @default.
• W2419541780 cites W1570770495 @default.
• W2419541780 cites W1737237432 @default.
• W2419541780 cites W1853745982 @default.
• W2419541780 cites W1959608418 @default.
• W2419541780 cites W1975593377 @default.
• W2419541780 cites W2008225289 @default.
• W2419541780 cites W2047834101 @default.
• W2419541780 cites W2049633694 @default.
• W2419541780 cites W2059503458 @default.
• W2419541780 cites W2083380015 @default.
• W2419541780 cites W2096192494 @default.
• W2419541780 cites W2097268041 @default.
• W2419541780 cites W2099878672 @default.
• W2419541780 cites W2105659727 @default.
• W2419541780 cites W2117853077 @default.
• W2419541780 cites W2119574220 @default.
• W2419541780 cites W2122262818 @default.
• W2419541780 cites W2130314481 @default.
• W2419541780 cites W2136922672 @default.
• W2419541780 cites W2137576513 @default.
• W2419541780 cites W2146571341 @default.
• W2419541780 cites W2157006255 @default.
• W2419541780 cites W2159080219 @default.
• W2419541780 cites W2161133254 @default.
• W2419541780 cites W2170678468 @default.
• W2419541780 cites W2216511711 @default.
• W2419541780 cites W2258283075 @default.
• W2419541780 cites W2296319761 @default.
• W2419541780 cites W2964121744 @default.
• W2419541780 cites W2072634211 @default.
• W2419541780 hasPublicationYear "2016" @default.
• W2419541780 type Work @default.
• W2419541780 sameAs 2419541780 @default.
• W2419541780 citedByCount "5" @default.
• W2419541780 countsByYear W24195417802017 @default.
• W2419541780 countsByYear W24195417802018 @default.
• W2419541780 countsByYear W24195417802019 @default.
• W2419541780 crossrefType "proceedings-article" @default.
• W2419541780 hasAuthorship W2419541780A5008391481 @default.
• W2419541780 hasAuthorship W2419541780A5016448581 @default.
• W2419541780 hasAuthorship W2419541780A5052576907 @default.
• W2419541780 hasAuthorship W2419541780A5056639842 @default.
• W2419541780 hasConcept C105795698 @default.
• W2419541780 hasConcept C11413529 @default.
• W2419541780 hasConcept C119857082 @default.
• W2419541780 hasConcept C126255220 @default.
• W2419541780 hasConcept C153258448 @default.
• W2419541780 hasConcept C154945302 @default.
• W2419541780 hasConcept C162324750 @default.
• W2419541780 hasConcept C185429906 @default.
• W2419541780 hasConcept C19499675 @default.
• W2419541780 hasConcept C2777303404 @default.
• W2419541780 hasConcept C33923547 @default.
• W2419541780 hasConcept C41008148 @default.
• W2419541780 hasConcept C49781872 @default.
• W2419541780 hasConcept C50522688 @default.
• W2419541780 hasConcept C50644808 @default.
• W2419541780 hasConcept C81388566 @default.
• W2419541780 hasConcept C9810830 @default.
• W2419541780 hasConceptScore W2419541780C105795698 @default.
• W2419541780 hasConceptScore W2419541780C11413529 @default.
• W2419541780 hasConceptScore W2419541780C119857082 @default.
• W2419541780 hasConceptScore W2419541780C126255220 @default.
• W2419541780 hasConceptScore W2419541780C153258448 @default.
• W2419541780 hasConceptScore W2419541780C154945302 @default.
• W2419541780 hasConceptScore W2419541780C162324750 @default.
• W2419541780 hasConceptScore W2419541780C185429906 @default.
• W2419541780 hasConceptScore W2419541780C19499675 @default.
• W2419541780 hasConceptScore W2419541780C2777303404 @default.
• W2419541780 hasConceptScore W2419541780C33923547 @default.
• W2419541780 hasConceptScore W2419541780C41008148 @default.
• W2419541780 hasConceptScore W2419541780C49781872 @default.
• W2419541780 hasConceptScore W2419541780C50522688 @default.
• W2419541780 hasConceptScore W2419541780C50644808 @default.
• W2419541780 hasConceptScore W2419541780C81388566 @default.
• W2419541780 hasConceptScore W2419541780C9810830 @default.
• W2419541780 hasLocation W24195417801 @default.
• W2419541780 hasOpenAccess W2419541780 @default.
• W2419541780 hasPrimaryLocation W24195417801 @default.
• W2419541780 hasRelatedWork W149076165 @default.
• W2419541780 hasRelatedWork W1592410721 @default.
• W2419541780 hasRelatedWork W2083721409 @default.
• W2419541780 hasRelatedWork W2122340819 @default.
• W2419541780 hasRelatedWork W2132588110 @default.
• W2419541780 hasRelatedWork W2136922672 @default.
• W2419541780 hasRelatedWork W2148721460 @default.
• W2419541780 hasRelatedWork W2177203353 @default.

• next