Matches in SemOpenAlex for { <https://semopenalex.org/work/W2103002107> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2103002107 abstract "A single neural network model developed from a limited amount of data usually lacks robustness. Thus combining multiple neural networks can enhance the neural network model performance. In this paper, a Bayesian combination method is developed for nonlinear dynamic process modelling and compared with simple averaging. Instead of using fixed combination weights, the estimated probability of a particular network being the true model is used as the combination weight for combining that network. A nearest neighbour method is used in estimating the network error for a given input data point, which is then used in calculating the combination weights for individual networks. The prior probability is estimated using the SSE of individual networks on a sliding window covering the most recent sampling times. It is shown that Bayesian combination generally outperforms simple averaging." @default.
- W2103002107 created "2016-06-24" @default.
- W2103002107 creator A5041978682 @default.
- W2103002107 creator A5052490084 @default.
- W2103002107 date "2004-06-22" @default.
- W2103002107 modified "2023-09-25" @default.
- W2103002107 title "Improving data based nonlinear process modelling through bayesian combination of multiple neural networks" @default.
- W2103002107 cites W1489209349 @default.
- W2103002107 cites W1538954065 @default.
- W2103002107 cites W1554663460 @default.
- W2103002107 cites W166951565 @default.
- W2103002107 cites W1966829527 @default.
- W2103002107 cites W1973941077 @default.
- W2103002107 cites W1982779742 @default.
- W2103002107 cites W1991859953 @default.
- W2103002107 cites W2007813324 @default.
- W2103002107 cites W2015860761 @default.
- W2103002107 cites W2016223002 @default.
- W2103002107 cites W2025653905 @default.
- W2103002107 cites W2032692564 @default.
- W2103002107 cites W2037570851 @default.
- W2103002107 cites W2073040595 @default.
- W2103002107 cites W2129357734 @default.
- W2103002107 cites W2133671888 @default.
- W2103002107 cites W2150884987 @default.
- W2103002107 cites W2156876426 @default.
- W2103002107 cites W28412257 @default.
- W2103002107 doi "https://doi.org/10.1109/ijcnn.2003.1223952" @default.
- W2103002107 hasPublicationYear "2004" @default.
- W2103002107 type Work @default.
- W2103002107 sameAs 2103002107 @default.
- W2103002107 citedByCount "1" @default.
- W2103002107 crossrefType "proceedings-article" @default.
- W2103002107 hasAuthorship W2103002107A5041978682 @default.
- W2103002107 hasAuthorship W2103002107A5052490084 @default.
- W2103002107 hasConcept C104317684 @default.
- W2103002107 hasConcept C107673813 @default.
- W2103002107 hasConcept C11413529 @default.
- W2103002107 hasConcept C119857082 @default.
- W2103002107 hasConcept C121332964 @default.
- W2103002107 hasConcept C124101348 @default.
- W2103002107 hasConcept C154945302 @default.
- W2103002107 hasConcept C158622935 @default.
- W2103002107 hasConcept C185592680 @default.
- W2103002107 hasConcept C33724603 @default.
- W2103002107 hasConcept C41008148 @default.
- W2103002107 hasConcept C50644808 @default.
- W2103002107 hasConcept C55493867 @default.
- W2103002107 hasConcept C62520636 @default.
- W2103002107 hasConcept C63479239 @default.
- W2103002107 hasConceptScore W2103002107C104317684 @default.
- W2103002107 hasConceptScore W2103002107C107673813 @default.
- W2103002107 hasConceptScore W2103002107C11413529 @default.
- W2103002107 hasConceptScore W2103002107C119857082 @default.
- W2103002107 hasConceptScore W2103002107C121332964 @default.
- W2103002107 hasConceptScore W2103002107C124101348 @default.
- W2103002107 hasConceptScore W2103002107C154945302 @default.
- W2103002107 hasConceptScore W2103002107C158622935 @default.
- W2103002107 hasConceptScore W2103002107C185592680 @default.
- W2103002107 hasConceptScore W2103002107C33724603 @default.
- W2103002107 hasConceptScore W2103002107C41008148 @default.
- W2103002107 hasConceptScore W2103002107C50644808 @default.
- W2103002107 hasConceptScore W2103002107C55493867 @default.
- W2103002107 hasConceptScore W2103002107C62520636 @default.
- W2103002107 hasConceptScore W2103002107C63479239 @default.
- W2103002107 hasLocation W21030021071 @default.
- W2103002107 hasOpenAccess W2103002107 @default.
- W2103002107 hasPrimaryLocation W21030021071 @default.
- W2103002107 hasRelatedWork W111669422 @default.
- W2103002107 hasRelatedWork W119149152 @default.
- W2103002107 hasRelatedWork W1593294636 @default.
- W2103002107 hasRelatedWork W1598201578 @default.
- W2103002107 hasRelatedWork W169049039 @default.
- W2103002107 hasRelatedWork W2796601240 @default.
- W2103002107 hasRelatedWork W2896984146 @default.
- W2103002107 hasRelatedWork W2907227398 @default.
- W2103002107 hasRelatedWork W2913747117 @default.
- W2103002107 hasRelatedWork W2964732440 @default.
- W2103002107 hasRelatedWork W3002165594 @default.
- W2103002107 hasRelatedWork W3003964003 @default.
- W2103002107 hasRelatedWork W3016928826 @default.
- W2103002107 hasRelatedWork W3103013643 @default.
- W2103002107 hasRelatedWork W3118641060 @default.
- W2103002107 hasRelatedWork W3146411230 @default.
- W2103002107 hasRelatedWork W31535252 @default.
- W2103002107 hasRelatedWork W322399760 @default.
- W2103002107 hasRelatedWork W32808555 @default.
- W2103002107 hasRelatedWork W1634486098 @default.
- W2103002107 isParatext "false" @default.
- W2103002107 isRetracted "false" @default.
- W2103002107 magId "2103002107" @default.
- W2103002107 workType "article" @default.