FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3045140839> ?p ?o ?g. }

• W3045140839 abstract "Graphical models are powerful tools for modeling high-dimensional data, but learning graphical models in the presence of latent variables is well-known to be difficult. In this work we give new results for learning Restricted Boltzmann Machines, probably the most well-studied class of latent variable models. Our results are based on new connections to learning two-layer neural networks under $ell_{infty}$ bounded input; for both problems, we give nearly optimal results under the conjectured hardness of sparse parity with noise. Using the connection between RBMs and feedforward networks, we also initiate the theoretical study of $supervised~RBMs$ [Hinton, 2012], a version of neural-network learning that couples distributional assumptions induced from the underlying graphical model with the architecture of the unknown function class. We then give an algorithm for learning a natural class of supervised RBMs with better runtime than what is possible for its related class of networks without distributional assumptions." @default.
• W3045140839 created "2020-07-29" @default.
• W3045140839 creator A5003106042 @default.
• W3045140839 creator A5006626709 @default.
• W3045140839 creator A5019144684 @default.
• W3045140839 date "2020-07-25" @default.
• W3045140839 modified "2023-09-27" @default.
• W3045140839 title "From Boltzmann Machines to Neural Networks and Back Again" @default.
• W3045140839 cites W1546851689 @default.
• W3045140839 cites W1584402024 @default.
• W3045140839 cites W1891181203 @default.
• W3045140839 cites W1964155876 @default.
• W3045140839 cites W1969880349 @default.
• W3045140839 cites W1977162457 @default.
• W3045140839 cites W1985813166 @default.
• W3045140839 cites W1987635176 @default.
• W3045140839 cites W2023683873 @default.
• W3045140839 cites W2054358802 @default.
• W3045140839 cites W2059242764 @default.
• W3045140839 cites W2064680241 @default.
• W3045140839 cites W2068524660 @default.
• W3045140839 cites W2080210666 @default.
• W3045140839 cites W2092685486 @default.
• W3045140839 cites W2099111195 @default.
• W3045140839 cites W2100495367 @default.
• W3045140839 cites W2108829665 @default.
• W3045140839 cites W2118858186 @default.
• W3045140839 cites W2119877753 @default.
• W3045140839 cites W2126229007 @default.
• W3045140839 cites W2128020980 @default.
• W3045140839 cites W2159080219 @default.
• W3045140839 cites W2163166770 @default.
• W3045140839 cites W2221366174 @default.
• W3045140839 cites W2558384550 @default.
• W3045140839 cites W2562573853 @default.
• W3045140839 cites W2566505556 @default.
• W3045140839 cites W2591714514 @default.
• W3045140839 cites W2750384547 @default.
• W3045140839 cites W2795291708 @default.
• W3045140839 cites W2895938368 @default.
• W3045140839 cites W2923228966 @default.
• W3045140839 cites W2951046202 @default.
• W3045140839 cites W2962767131 @default.
• W3045140839 cites W2963266994 @default.
• W3045140839 cites W2963519230 @default.
• W3045140839 cites W2963574294 @default.
• W3045140839 cites W2963623651 @default.
• W3045140839 cites W2963672337 @default.
• W3045140839 cites W2963744427 @default.
• W3045140839 cites W2963827833 @default.
• W3045140839 cites W2963992434 @default.
• W3045140839 cites W2964071831 @default.
• W3045140839 cites W2964308567 @default.
• W3045140839 cites W3037567475 @default.
• W3045140839 cites W3081001064 @default.
• W3045140839 cites W44815768 @default.
• W3045140839 cites W607505555 @default.
• W3045140839 hasPublicationYear "2020" @default.
• W3045140839 type Work @default.
• W3045140839 sameAs 3045140839 @default.
• W3045140839 citedByCount "0" @default.
• W3045140839 crossrefType "posted-content" @default.
• W3045140839 hasAuthorship W3045140839A5003106042 @default.
• W3045140839 hasAuthorship W3045140839A5006626709 @default.
• W3045140839 hasAuthorship W3045140839A5019144684 @default.
• W3045140839 hasConcept C119857082 @default.
• W3045140839 hasConcept C134306372 @default.
• W3045140839 hasConcept C154945302 @default.
• W3045140839 hasConcept C155846161 @default.
• W3045140839 hasConcept C192576344 @default.
• W3045140839 hasConcept C199354608 @default.
• W3045140839 hasConcept C2777212361 @default.
• W3045140839 hasConcept C33923547 @default.
• W3045140839 hasConcept C34388435 @default.
• W3045140839 hasConcept C41008148 @default.
• W3045140839 hasConcept C50644808 @default.
• W3045140839 hasConcept C51167844 @default.
• W3045140839 hasConcept C80444323 @default.
• W3045140839 hasConceptScore W3045140839C119857082 @default.
• W3045140839 hasConceptScore W3045140839C134306372 @default.
• W3045140839 hasConceptScore W3045140839C154945302 @default.
• W3045140839 hasConceptScore W3045140839C155846161 @default.
• W3045140839 hasConceptScore W3045140839C192576344 @default.
• W3045140839 hasConceptScore W3045140839C199354608 @default.
• W3045140839 hasConceptScore W3045140839C2777212361 @default.
• W3045140839 hasConceptScore W3045140839C33923547 @default.
• W3045140839 hasConceptScore W3045140839C34388435 @default.
• W3045140839 hasConceptScore W3045140839C41008148 @default.
• W3045140839 hasConceptScore W3045140839C50644808 @default.
• W3045140839 hasConceptScore W3045140839C51167844 @default.
• W3045140839 hasConceptScore W3045140839C80444323 @default.
• W3045140839 hasLocation W30451408391 @default.
• W3045140839 hasOpenAccess W3045140839 @default.
• W3045140839 hasPrimaryLocation W30451408391 @default.
• W3045140839 hasRelatedWork W2080961666 @default.
• W3045140839 hasRelatedWork W254850126 @default.
• W3045140839 hasRelatedWork W2567167069 @default.
• W3045140839 hasRelatedWork W2803439868 @default.
• W3045140839 hasRelatedWork W2912029373 @default.
• W3045140839 hasRelatedWork W2921407516 @default.

• next