Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310332698> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4310332698 endingPage "1" @default.
- W4310332698 startingPage "1" @default.
- W4310332698 abstract "We consider the reconstruction of brain activity from electroencephalography (EEG). This inverse problem can be formulated as a linear regression with independent Gaussian scale mixture priors for both the source and noise components. Crucial factors influencing the accuracy of the source estimation are not only the noise level but also its correlation structure, but existing approaches have not addressed the estimation of noise covariance matrices with full structure. To address this shortcoming, we develop hierarchical Bayesian (type-II maximum likelihood) models for observations with latent variables for source and noise, which are estimated jointly from data. As an extension to classical sparse Bayesian learning (SBL), where across-sensor observations are assumed to be independent and identically distributed, we consider Gaussian noise with full covariance structure. Using the majorization-maximization framework and Riemannian geometry, we derive an efficient algorithm for updating the noise covariance along the manifold of positive definite matrices. We demonstrate that our algorithm has guaranteed and fast convergence and validate it in simulations and with real MEG data. Our results demonstrate that the novel framework significantly improves upon state-of-the-art techniques in the real-world scenario where the noise is indeed non-diagonal and fullstructured. Our method has applications in many domains beyond biomagnetic inverse problems." @default.
- W4310332698 created "2022-12-08" @default.
- W4310332698 creator A5019656529 @default.
- W4310332698 creator A5035006868 @default.
- W4310332698 creator A5037410761 @default.
- W4310332698 creator A5041848182 @default.
- W4310332698 creator A5068256213 @default.
- W4310332698 creator A5072994165 @default.
- W4310332698 creator A5078446909 @default.
- W4310332698 date "2022-01-01" @default.
- W4310332698 modified "2023-10-15" @default.
- W4310332698 title "Joint Learning of Full-structure Noise in Hierarchical Bayesian Regression Models" @default.
- W4310332698 doi "https://doi.org/10.1109/tmi.2022.3224085" @default.
- W4310332698 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36423312" @default.
- W4310332698 hasPublicationYear "2022" @default.
- W4310332698 type Work @default.
- W4310332698 citedByCount "3" @default.
- W4310332698 countsByYear W43103326982022 @default.
- W4310332698 countsByYear W43103326982023 @default.
- W4310332698 crossrefType "journal-article" @default.
- W4310332698 hasAuthorship W4310332698A5019656529 @default.
- W4310332698 hasAuthorship W4310332698A5035006868 @default.
- W4310332698 hasAuthorship W4310332698A5037410761 @default.
- W4310332698 hasAuthorship W4310332698A5041848182 @default.
- W4310332698 hasAuthorship W4310332698A5068256213 @default.
- W4310332698 hasAuthorship W4310332698A5072994165 @default.
- W4310332698 hasAuthorship W4310332698A5078446909 @default.
- W4310332698 hasBestOaLocation W43103326982 @default.
- W4310332698 hasConcept C105795698 @default.
- W4310332698 hasConcept C107673813 @default.
- W4310332698 hasConcept C11413529 @default.
- W4310332698 hasConcept C115961682 @default.
- W4310332698 hasConcept C122123141 @default.
- W4310332698 hasConcept C141513077 @default.
- W4310332698 hasConcept C153180895 @default.
- W4310332698 hasConcept C154945302 @default.
- W4310332698 hasConcept C177769412 @default.
- W4310332698 hasConcept C178650346 @default.
- W4310332698 hasConcept C180877172 @default.
- W4310332698 hasConcept C185142706 @default.
- W4310332698 hasConcept C33923547 @default.
- W4310332698 hasConcept C41008148 @default.
- W4310332698 hasConcept C4199805 @default.
- W4310332698 hasConcept C99498987 @default.
- W4310332698 hasConceptScore W4310332698C105795698 @default.
- W4310332698 hasConceptScore W4310332698C107673813 @default.
- W4310332698 hasConceptScore W4310332698C11413529 @default.
- W4310332698 hasConceptScore W4310332698C115961682 @default.
- W4310332698 hasConceptScore W4310332698C122123141 @default.
- W4310332698 hasConceptScore W4310332698C141513077 @default.
- W4310332698 hasConceptScore W4310332698C153180895 @default.
- W4310332698 hasConceptScore W4310332698C154945302 @default.
- W4310332698 hasConceptScore W4310332698C177769412 @default.
- W4310332698 hasConceptScore W4310332698C178650346 @default.
- W4310332698 hasConceptScore W4310332698C180877172 @default.
- W4310332698 hasConceptScore W4310332698C185142706 @default.
- W4310332698 hasConceptScore W4310332698C33923547 @default.
- W4310332698 hasConceptScore W4310332698C41008148 @default.
- W4310332698 hasConceptScore W4310332698C4199805 @default.
- W4310332698 hasConceptScore W4310332698C99498987 @default.
- W4310332698 hasFunder F4320306078 @default.
- W4310332698 hasFunder F4320320879 @default.
- W4310332698 hasFunder F4320321001 @default.
- W4310332698 hasFunder F4320321114 @default.
- W4310332698 hasFunder F4320321260 @default.
- W4310332698 hasFunder F4320337376 @default.
- W4310332698 hasFunder F4320338335 @default.
- W4310332698 hasLocation W43103326981 @default.
- W4310332698 hasLocation W43103326982 @default.
- W4310332698 hasLocation W43103326983 @default.
- W4310332698 hasOpenAccess W4310332698 @default.
- W4310332698 hasPrimaryLocation W43103326981 @default.
- W4310332698 hasRelatedWork W1899642730 @default.
- W4310332698 hasRelatedWork W1910942334 @default.
- W4310332698 hasRelatedWork W1952774054 @default.
- W4310332698 hasRelatedWork W1963776785 @default.
- W4310332698 hasRelatedWork W2018617091 @default.
- W4310332698 hasRelatedWork W2028826930 @default.
- W4310332698 hasRelatedWork W2093410015 @default.
- W4310332698 hasRelatedWork W2104726544 @default.
- W4310332698 hasRelatedWork W2189092608 @default.
- W4310332698 hasRelatedWork W2740506553 @default.
- W4310332698 isParatext "false" @default.
- W4310332698 isRetracted "false" @default.
- W4310332698 workType "article" @default.