FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912451899> ?p ?o ?g. }

• W2912451899 abstract "One main result of this dissertation is the development of Metric Gaussian Variational Inference (MGVI), a method to perform approximate inference in extremely high dimensions and for complex probabilistic models. The problem with high-dimensional and complex models is twofold. Fist, to capture the true posterior distribution accurately, a sufficiently rich approximation for it is required. Second, the number of parameters to express this richness scales dramatically with the number of model parameters. For example, explicitly expressing the correlation between all model parameters requires their squared number of correlation coefficients. In settings with millions of model parameter, this is unfeasible.MGVI overcomes this limitation by replacing the explicit covariance with an implicit approximation, which does not have to be stored and is accessed via samples. This procedure scales linearly with the problem size and allows to account for the full correlations in even extremely large problems. This makes it also applicable to significantly more complex setups. MGVI enabled a series of ambitious signal reconstructions by me and others, which will be showcased. This involves a time- and frequency-resolved reconstruction of the shadow around the black hole M87* using data provided by the Event Horizon Telescope Collaboration, a three-dimensional tomographic reconstruction of interstellar dust within 300pc around the sun from Gaia starlight-absorption and parallax data, novel medical imaging methods for computed tomography, an all-sky Faraday rotation map, combining distinct data sources, and simultaneous calibration and imaging with a radio-interferometer.The second main result is an an approach to use several, independently trained and deep neural networks to reason on complex tasks. Deep learning allows to capture abstract concepts by extracting them from large amounts of training data, which alleviates the necessity of an explicit mathematical formulation. Here a generative neural network is used as a prior distribution and certain properties are imposed via classification and regression networks. The inference is then performed in terms of the latent variables of the generator, which is done using MGVI and other methods. This allows to flexibly answer novel questions without having to re-train any neural network and to come up with novel answers through Bayesian reasoning. This novel approach of Bayesian reasoning with neural networks can also be combined with conventional measurement data." @default.
• W2912451899 created "2019-02-21" @default.
• W2912451899 creator A5067841492 @default.
• W2912451899 creator A5075381731 @default.
• W2912451899 date "2019-01-30" @default.
• W2912451899 modified "2023-09-23" @default.
• W2912451899 title "Metric Gaussian Variational Inference." @default.
• W2912451899 cites W1479979375 @default.
• W2912451899 cites W1506806321 @default.
• W2912451899 cites W1510355813 @default.
• W2912451899 cites W1545319692 @default.
• W2912451899 cites W1857053476 @default.
• W2912451899 cites W1905898145 @default.
• W2912451899 cites W1927271208 @default.
• W2912451899 cites W1965555277 @default.
• W2912451899 cites W1981457167 @default.
• W2912451899 cites W2031988475 @default.
• W2912451899 cites W2036084078 @default.
• W2912451899 cites W2059448777 @default.
• W2912451899 cites W2070058271 @default.
• W2912451899 cites W2080829915 @default.
• W2912451899 cites W2081979658 @default.
• W2912451899 cites W2098841537 @default.
• W2912451899 cites W2133840092 @default.
• W2912451899 cites W2134364569 @default.
• W2912451899 cites W2139385756 @default.
• W2912451899 cites W2157826563 @default.
• W2912451899 cites W2167729035 @default.
• W2912451899 cites W2187471809 @default.
• W2912451899 cites W2485135680 @default.
• W2912451899 cites W2612111819 @default.
• W2912451899 cites W2778699422 @default.
• W2912451899 cites W2905325477 @default.
• W2912451899 cites W2913018314 @default.
• W2912451899 cites W2951004968 @default.
• W2912451899 cites W2962994101 @default.
• W2912451899 cites W2963161900 @default.
• W2912451899 cites W2963349468 @default.
• W2912451899 cites W2963736577 @default.
• W2912451899 cites W3013012439 @default.
• W2912451899 cites W3086499488 @default.
• W2912451899 cites W3103480513 @default.
• W2912451899 cites W3104819538 @default.
• W2912451899 cites W74240361 @default.
• W2912451899 hasPublicationYear "2019" @default.
• W2912451899 type Work @default.
• W2912451899 sameAs 2912451899 @default.
• W2912451899 citedByCount "7" @default.
• W2912451899 countsByYear W29124518992020 @default.
• W2912451899 countsByYear W29124518992021 @default.
• W2912451899 crossrefType "posted-content" @default.
• W2912451899 hasAuthorship W2912451899A5067841492 @default.
• W2912451899 hasAuthorship W2912451899A5075381731 @default.
• W2912451899 hasConcept C105795698 @default.
• W2912451899 hasConcept C11413529 @default.
• W2912451899 hasConcept C121332964 @default.
• W2912451899 hasConcept C141379421 @default.
• W2912451899 hasConcept C154945302 @default.
• W2912451899 hasConcept C162324750 @default.
• W2912451899 hasConcept C163716315 @default.
• W2912451899 hasConcept C176217482 @default.
• W2912451899 hasConcept C178650346 @default.
• W2912451899 hasConcept C21547014 @default.
• W2912451899 hasConcept C2776214188 @default.
• W2912451899 hasConcept C2779363554 @default.
• W2912451899 hasConcept C33923547 @default.
• W2912451899 hasConcept C41008148 @default.
• W2912451899 hasConcept C61326573 @default.
• W2912451899 hasConcept C62520636 @default.
• W2912451899 hasConcept C97742081 @default.
• W2912451899 hasConceptScore W2912451899C105795698 @default.
• W2912451899 hasConceptScore W2912451899C11413529 @default.
• W2912451899 hasConceptScore W2912451899C121332964 @default.
• W2912451899 hasConceptScore W2912451899C141379421 @default.
• W2912451899 hasConceptScore W2912451899C154945302 @default.
• W2912451899 hasConceptScore W2912451899C162324750 @default.
• W2912451899 hasConceptScore W2912451899C163716315 @default.
• W2912451899 hasConceptScore W2912451899C176217482 @default.
• W2912451899 hasConceptScore W2912451899C178650346 @default.
• W2912451899 hasConceptScore W2912451899C21547014 @default.
• W2912451899 hasConceptScore W2912451899C2776214188 @default.
• W2912451899 hasConceptScore W2912451899C2779363554 @default.
• W2912451899 hasConceptScore W2912451899C33923547 @default.
• W2912451899 hasConceptScore W2912451899C41008148 @default.
• W2912451899 hasConceptScore W2912451899C61326573 @default.
• W2912451899 hasConceptScore W2912451899C62520636 @default.
• W2912451899 hasConceptScore W2912451899C97742081 @default.
• W2912451899 hasOpenAccess W2912451899 @default.
• W2912451899 hasRelatedWork W2022511650 @default.
• W2912451899 hasRelatedWork W2093666167 @default.
• W2912451899 hasRelatedWork W2166851633 @default.
• W2912451899 hasRelatedWork W2793288892 @default.
• W2912451899 hasRelatedWork W2805874067 @default.
• W2912451899 hasRelatedWork W2892095597 @default.
• W2912451899 hasRelatedWork W2904088711 @default.
• W2912451899 hasRelatedWork W2945883617 @default.
• W2912451899 hasRelatedWork W2962994101 @default.
• W2912451899 hasRelatedWork W2985844698 @default.
• W2912451899 hasRelatedWork W3006561566 @default.
• W2912451899 hasRelatedWork W3016921898 @default.

• next