FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3011322992> ?p ?o ?g. }

• W3011322992 endingPage "1017" @default.
• W3011322992 startingPage "969" @default.
• W3011322992 abstract "Abstract The Kalman filter provides a simple and efficient algorithm to compute the posterior distribution for state-space models where both the latent state and measurement models are linear and gaussian. Extensions to the Kalman filter, including the extended and unscented Kalman filters, incorporate linearizations for models where the observation model p(observation|state) is nonlinear. We argue that in many cases, a model for p(state|observation) proves both easier to learn and more accurate for latent state estimation. Approximating p(state|observation) as gaussian leads to a new filtering algorithm, the discriminative Kalman filter (DKF), which can perform well even when p(observation|state) is highly nonlinear and/or nongaussian. The approximation, motivated by the Bernstein–von Mises theorem, improves as the dimensionality of the observations increases. The DKF has computational complexity similar to the Kalman filter, allowing it in some cases to perform much faster than particle filters with similar precision, while better accounting for nonlinear and nongaussian observation models than Kalman-based extensions. When the observation model must be learned from training data prior to filtering, off-the-shelf nonlinear and nonparametric regression techniques can provide a gaussian model for p(observation|state) that cleanly integrates with the DKF. As part of the BrainGate2 clinical trial, we successfully implemented gaussian process regression with the DKF framework in a brain-computer interface to provide real-time, closed-loop cursor control to a person with a complete spinal cord injury. In this letter, we explore the theory underlying the DKF, exhibit some illustrative examples, and outline potential extensions." @default.
• W3011322992 created "2020-03-23" @default.
• W3011322992 creator A5005277906 @default.
• W3011322992 creator A5032110460 @default.
• W3011322992 creator A5034257495 @default.
• W3011322992 creator A5067962267 @default.
• W3011322992 creator A5090070625 @default.
• W3011322992 date "2020-05-01" @default.
• W3011322992 modified "2023-10-18" @default.
• W3011322992 title "The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Nongaussian Observation Models" @default.
• W3011322992 cites W1460189015 @default.
• W3011322992 cites W1933639893 @default.
• W3011322992 cites W1964491684 @default.
• W3011322992 cites W1966679339 @default.
• W3011322992 cites W1978610990 @default.
• W3011322992 cites W1978913152 @default.
• W3011322992 cites W1980586072 @default.
• W3011322992 cites W2005775198 @default.
• W3011322992 cites W2006285431 @default.
• W3011322992 cites W2009664245 @default.
• W3011322992 cites W2020769260 @default.
• W3011322992 cites W2020934227 @default.
• W3011322992 cites W2033144847 @default.
• W3011322992 cites W2043357888 @default.
• W3011322992 cites W2051203581 @default.
• W3011322992 cites W2052920959 @default.
• W3011322992 cites W2054091988 @default.
• W3011322992 cites W2055936398 @default.
• W3011322992 cites W2064675550 @default.
• W3011322992 cites W2067982677 @default.
• W3011322992 cites W2071127089 @default.
• W3011322992 cites W2072403451 @default.
• W3011322992 cites W2073283839 @default.
• W3011322992 cites W2074613775 @default.
• W3011322992 cites W2076063813 @default.
• W3011322992 cites W2076186907 @default.
• W3011322992 cites W2083402998 @default.
• W3011322992 cites W2087070363 @default.
• W3011322992 cites W2087185095 @default.
• W3011322992 cites W2087435860 @default.
• W3011322992 cites W2088112392 @default.
• W3011322992 cites W2092789011 @default.
• W3011322992 cites W2098613108 @default.
• W3011322992 cites W2099371695 @default.
• W3011322992 cites W2102716594 @default.
• W3011322992 cites W2105934661 @default.
• W3011322992 cites W2106006415 @default.
• W3011322992 cites W2108381339 @default.
• W3011322992 cites W2113373687 @default.
• W3011322992 cites W2119432914 @default.
• W3011322992 cites W2119774068 @default.
• W3011322992 cites W2126736494 @default.
• W3011322992 cites W2136032750 @default.
• W3011322992 cites W2136848157 @default.
• W3011322992 cites W2138688580 @default.
• W3011322992 cites W2146693544 @default.
• W3011322992 cites W2149331527 @default.
• W3011322992 cites W2152225095 @default.
• W3011322992 cites W2155482699 @default.
• W3011322992 cites W2157098139 @default.
• W3011322992 cites W2160337655 @default.
• W3011322992 cites W2160444846 @default.
• W3011322992 cites W2161358768 @default.
• W3011322992 cites W2171457973 @default.
• W3011322992 cites W2223658335 @default.
• W3011322992 cites W2243428647 @default.
• W3011322992 cites W2256578114 @default.
• W3011322992 cites W2341256599 @default.
• W3011322992 cites W2538079766 @default.
• W3011322992 cites W2538865650 @default.
• W3011322992 cites W2589952473 @default.
• W3011322992 cites W2592815340 @default.
• W3011322992 cites W2603380332 @default.
• W3011322992 cites W2784349096 @default.
• W3011322992 cites W2889870209 @default.
• W3011322992 cites W2901154643 @default.
• W3011322992 cites W2911546748 @default.
• W3011322992 cites W2951777958 @default.
• W3011322992 cites W2985140334 @default.
• W3011322992 cites W371215106 @default.
• W3011322992 cites W4232464081 @default.
• W3011322992 cites W4239127880 @default.
• W3011322992 cites W4250389103 @default.
• W3011322992 cites W4251960031 @default.
• W3011322992 cites W91088564 @default.
• W3011322992 doi "https://doi.org/10.1162/neco_a_01275" @default.
• W3011322992 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8259355" @default.
• W3011322992 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32187000" @default.
• W3011322992 hasPublicationYear "2020" @default.
• W3011322992 type Work @default.
• W3011322992 sameAs 3011322992 @default.
• W3011322992 citedByCount "10" @default.
• W3011322992 countsByYear W30113229922021 @default.
• W3011322992 countsByYear W30113229922022 @default.
• W3011322992 countsByYear W30113229922023 @default.
• W3011322992 crossrefType "journal-article" @default.
• W3011322992 hasAuthorship W3011322992A5005277906 @default.
• W3011322992 hasAuthorship W3011322992A5032110460 @default.

• next