Matches in SemOpenAlex for { <https://semopenalex.org/work/W1983840995> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W1983840995 endingPage "1343" @default.
- W1983840995 startingPage "1328" @default.
- W1983840995 abstract "Although there are many neural network (NN) algorithms for prediction and for control, and although methods for optimal estimation (including filtering and prediction) and for optimal control in linear systems were provided by Kalman in 1960 (with nonlinear extensions since then), there has been, to my knowledge, no NN algorithm that learns either Kalman prediction or Kalman control (apart from the special case of stationary control). Here we show how optimal Kalman prediction and control (KPC), as well as system identification, can be learned and executed by a recurrent neural network composed of linear-response nodes, using as input only a stream of noisy measurement data. The requirements of KPC appear to impose significant constraints on the allowed NN circuitry and signal flows. The NN architecture implied by these constraints bears certain resemblances to the local-circuit architecture of mammalian cerebral cortex. We discuss these resemblances, as well as caveats that limit our current ability to draw inferences for biological function. It has been suggested that the local cortical circuit (LCC) architecture may perform core functions (as yet unknown) that underlie sensory, motor, and other cortical processing. It is reasonable to conjecture that such functions may include prediction, the estimation or inference of missing or noisy sensory data, and the goal-driven generation of control signals. The resemblances found between the KPC NN architecture and that of the LCC are consistent with this conjecture." @default.
- W1983840995 created "2016-06-24" @default.
- W1983840995 creator A5050183326 @default.
- W1983840995 date "2008-11-01" @default.
- W1983840995 modified "2023-09-24" @default.
- W1983840995 title "Neural network learning of optimal Kalman prediction and control" @default.
- W1983840995 cites W1570688454 @default.
- W1983840995 cites W1981578159 @default.
- W1983840995 cites W1981814724 @default.
- W1983840995 cites W1983792941 @default.
- W1983840995 cites W1986178142 @default.
- W1983840995 cites W2013821013 @default.
- W1983840995 cites W2028031284 @default.
- W1983840995 cites W2032677875 @default.
- W1983840995 cites W2063971957 @default.
- W1983840995 cites W2097376330 @default.
- W1983840995 cites W2099169325 @default.
- W1983840995 cites W2101305876 @default.
- W1983840995 cites W2101576232 @default.
- W1983840995 cites W2105934661 @default.
- W1983840995 cites W2114876443 @default.
- W1983840995 cites W2120772353 @default.
- W1983840995 cites W2123806929 @default.
- W1983840995 cites W2125663122 @default.
- W1983840995 cites W2133861842 @default.
- W1983840995 cites W2136922672 @default.
- W1983840995 cites W2138179494 @default.
- W1983840995 cites W2148336939 @default.
- W1983840995 cites W2148848065 @default.
- W1983840995 cites W2151718948 @default.
- W1983840995 cites W2169791674 @default.
- W1983840995 doi "https://doi.org/10.1016/j.neunet.2008.05.002" @default.
- W1983840995 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/18602247" @default.
- W1983840995 hasPublicationYear "2008" @default.
- W1983840995 type Work @default.
- W1983840995 sameAs 1983840995 @default.
- W1983840995 citedByCount "25" @default.
- W1983840995 countsByYear W19838409952012 @default.
- W1983840995 countsByYear W19838409952013 @default.
- W1983840995 countsByYear W19838409952014 @default.
- W1983840995 countsByYear W19838409952015 @default.
- W1983840995 countsByYear W19838409952016 @default.
- W1983840995 countsByYear W19838409952017 @default.
- W1983840995 countsByYear W19838409952019 @default.
- W1983840995 countsByYear W19838409952021 @default.
- W1983840995 countsByYear W19838409952023 @default.
- W1983840995 crossrefType "journal-article" @default.
- W1983840995 hasAuthorship W1983840995A5050183326 @default.
- W1983840995 hasBestOaLocation W19838409952 @default.
- W1983840995 hasConcept C119857082 @default.
- W1983840995 hasConcept C126255220 @default.
- W1983840995 hasConcept C14036430 @default.
- W1983840995 hasConcept C154945302 @default.
- W1983840995 hasConcept C157286648 @default.
- W1983840995 hasConcept C2775924081 @default.
- W1983840995 hasConcept C2776214188 @default.
- W1983840995 hasConcept C33923547 @default.
- W1983840995 hasConcept C41008148 @default.
- W1983840995 hasConcept C47446073 @default.
- W1983840995 hasConcept C50644808 @default.
- W1983840995 hasConcept C78458016 @default.
- W1983840995 hasConcept C86803240 @default.
- W1983840995 hasConcept C91575142 @default.
- W1983840995 hasConceptScore W1983840995C119857082 @default.
- W1983840995 hasConceptScore W1983840995C126255220 @default.
- W1983840995 hasConceptScore W1983840995C14036430 @default.
- W1983840995 hasConceptScore W1983840995C154945302 @default.
- W1983840995 hasConceptScore W1983840995C157286648 @default.
- W1983840995 hasConceptScore W1983840995C2775924081 @default.
- W1983840995 hasConceptScore W1983840995C2776214188 @default.
- W1983840995 hasConceptScore W1983840995C33923547 @default.
- W1983840995 hasConceptScore W1983840995C41008148 @default.
- W1983840995 hasConceptScore W1983840995C47446073 @default.
- W1983840995 hasConceptScore W1983840995C50644808 @default.
- W1983840995 hasConceptScore W1983840995C78458016 @default.
- W1983840995 hasConceptScore W1983840995C86803240 @default.
- W1983840995 hasConceptScore W1983840995C91575142 @default.
- W1983840995 hasIssue "9" @default.
- W1983840995 hasLocation W19838409951 @default.
- W1983840995 hasLocation W19838409952 @default.
- W1983840995 hasLocation W19838409953 @default.
- W1983840995 hasOpenAccess W1983840995 @default.
- W1983840995 hasPrimaryLocation W19838409951 @default.
- W1983840995 hasRelatedWork W2386387936 @default.
- W1983840995 hasRelatedWork W2961085424 @default.
- W1983840995 hasRelatedWork W3046775127 @default.
- W1983840995 hasRelatedWork W3170094116 @default.
- W1983840995 hasRelatedWork W4205958290 @default.
- W1983840995 hasRelatedWork W4285260836 @default.
- W1983840995 hasRelatedWork W4286629047 @default.
- W1983840995 hasRelatedWork W4306321456 @default.
- W1983840995 hasRelatedWork W4306674287 @default.
- W1983840995 hasRelatedWork W4224009465 @default.
- W1983840995 hasVolume "21" @default.
- W1983840995 isParatext "false" @default.
- W1983840995 isRetracted "false" @default.
- W1983840995 magId "1983840995" @default.
- W1983840995 workType "article" @default.