Matches in SemOpenAlex for { <https://semopenalex.org/work/W36798916> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W36798916 abstract "We view perceptual tasks such as vision and speech recognition as inference problems where the goal is to estimate the posterior distribution over latent variables (e.g., depth in stereo vision) given the sensory input. The recent flurry of research in independent component analysis exemplifies the importance of inferring the continuousvalued latent variables of input data. The latent variables found by this method are linearly related to the input, but perception requires nonlinear inferences such as decision-making. Even continuous latent variables such as depth are nonlinearly related to the input. In this paper, we present a unifying framework for stochastic neural networks with nonlinear latent variables. Nonlinear units are obtained by passing the outputs of linear Gaussian units through various nonlinearities. We present a general variational method that maximizes a lower bound on the likelihood of a training set, and give results on two visual feature extraction problems." @default.
- W36798916 created "2016-06-24" @default.
- W36798916 creator A5003361977 @default.
- W36798916 creator A5024209719 @default.
- W36798916 date "2001-01-01" @default.
- W36798916 modified "2023-09-24" @default.
- W36798916 title "Variational Learning in Nonlinear Gaussian Belief Networks" @default.
- W36798916 cites W1520168181 @default.
- W36798916 cites W1520448186 @default.
- W36798916 cites W1547224907 @default.
- W36798916 cites W1662191912 @default.
- W36798916 cites W1810424324 @default.
- W36798916 cites W1981814724 @default.
- W36798916 cites W1993845689 @default.
- W36798916 cites W2026799324 @default.
- W36798916 cites W2063089147 @default.
- W36798916 cites W2063971957 @default.
- W36798916 cites W2083380015 @default.
- W36798916 cites W2100266635 @default.
- W36798916 cites W2105659727 @default.
- W36798916 cites W2108384452 @default.
- W36798916 cites W2133069808 @default.
- W36798916 cites W2145889472 @default.
- W36798916 cites W2149239179 @default.
- W36798916 cites W2153443573 @default.
- W36798916 cites W2156452366 @default.
- W36798916 cites W2170858534 @default.
- W36798916 cites W2620898487 @default.
- W36798916 cites W52127214 @default.
- W36798916 cites W3178912857 @default.
- W36798916 doi "https://doi.org/10.7551/mitpress/3349.003.0011" @default.
- W36798916 hasPublicationYear "2001" @default.
- W36798916 type Work @default.
- W36798916 sameAs 36798916 @default.
- W36798916 citedByCount "0" @default.
- W36798916 crossrefType "book-chapter" @default.
- W36798916 hasAuthorship W36798916A5003361977 @default.
- W36798916 hasAuthorship W36798916A5024209719 @default.
- W36798916 hasConcept C119857082 @default.
- W36798916 hasConcept C121332964 @default.
- W36798916 hasConcept C137002209 @default.
- W36798916 hasConcept C153180895 @default.
- W36798916 hasConcept C154945302 @default.
- W36798916 hasConcept C158622935 @default.
- W36798916 hasConcept C163716315 @default.
- W36798916 hasConcept C177264268 @default.
- W36798916 hasConcept C199360897 @default.
- W36798916 hasConcept C2776214188 @default.
- W36798916 hasConcept C33923547 @default.
- W36798916 hasConcept C41008148 @default.
- W36798916 hasConcept C50644808 @default.
- W36798916 hasConcept C51167844 @default.
- W36798916 hasConcept C62520636 @default.
- W36798916 hasConcept C65965080 @default.
- W36798916 hasConcept C84114770 @default.
- W36798916 hasConceptScore W36798916C119857082 @default.
- W36798916 hasConceptScore W36798916C121332964 @default.
- W36798916 hasConceptScore W36798916C137002209 @default.
- W36798916 hasConceptScore W36798916C153180895 @default.
- W36798916 hasConceptScore W36798916C154945302 @default.
- W36798916 hasConceptScore W36798916C158622935 @default.
- W36798916 hasConceptScore W36798916C163716315 @default.
- W36798916 hasConceptScore W36798916C177264268 @default.
- W36798916 hasConceptScore W36798916C199360897 @default.
- W36798916 hasConceptScore W36798916C2776214188 @default.
- W36798916 hasConceptScore W36798916C33923547 @default.
- W36798916 hasConceptScore W36798916C41008148 @default.
- W36798916 hasConceptScore W36798916C50644808 @default.
- W36798916 hasConceptScore W36798916C51167844 @default.
- W36798916 hasConceptScore W36798916C62520636 @default.
- W36798916 hasConceptScore W36798916C65965080 @default.
- W36798916 hasConceptScore W36798916C84114770 @default.
- W36798916 hasLocation W367989161 @default.
- W36798916 hasOpenAccess W36798916 @default.
- W36798916 hasPrimaryLocation W367989161 @default.
- W36798916 hasRelatedWork W1530965581 @default.
- W36798916 hasRelatedWork W1565153955 @default.
- W36798916 hasRelatedWork W1967241879 @default.
- W36798916 hasRelatedWork W1985495776 @default.
- W36798916 hasRelatedWork W2073219746 @default.
- W36798916 hasRelatedWork W2074989593 @default.
- W36798916 hasRelatedWork W2118771085 @default.
- W36798916 hasRelatedWork W2124592697 @default.
- W36798916 hasRelatedWork W2337805204 @default.
- W36798916 hasRelatedWork W2415469094 @default.
- W36798916 hasRelatedWork W2526688286 @default.
- W36798916 hasRelatedWork W2750536545 @default.
- W36798916 hasRelatedWork W2913259400 @default.
- W36798916 hasRelatedWork W2963474899 @default.
- W36798916 hasRelatedWork W2963567641 @default.
- W36798916 hasRelatedWork W2974677805 @default.
- W36798916 hasRelatedWork W3098217967 @default.
- W36798916 hasRelatedWork W3107298060 @default.
- W36798916 hasRelatedWork W3142873477 @default.
- W36798916 hasRelatedWork W8656678 @default.
- W36798916 isParatext "false" @default.
- W36798916 isRetracted "false" @default.
- W36798916 magId "36798916" @default.
- W36798916 workType "book-chapter" @default.