FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2922146890> ?p ?o ?g. }

• W2922146890 endingPage "75" @default.
• W2922146890 startingPage "62" @default.
• W2922146890 abstract "Parameter learning is an important aspect of learning in Bayesian networks. Although the maximum likelihood algorithm is often effective, it suffers from overfitting when there is insufficient data. To address this, prior distributions of model parameters are often imposed. When training a Bayesian network, the parameters of the network are optimized to fit the data. However, imposing prior distributions can reduce the fitness between parameters and data. Therefore, a trade-off is needed between fitting and overfitting. In this study, a new algorithm, named MiniMax Fitness (MMF) is developed to address this problem. The method includes three main steps. First, the maximum a posterior estimation that combines data and prior distribution is derived. Then, the hyper-parameters of the prior distribution are optimized to minimize the fitness between posterior estimation and data. Finally, the order of posterior estimation is checked and adjusted to match the order of the statistical counts from the data. In addition, we introduce an improved constrained maximum entropy method, named Prior Free Constrained Maximum Entropy (PF-CME), to facilitate parameter learning when domain knowledge is provided. Experiments show that the proposed methods outperforms most of existing parameter learning methods." @default.
• W2922146890 created "2019-03-22" @default.
• W2922146890 creator A5005364117 @default.
• W2922146890 creator A5011685930 @default.
• W2922146890 creator A5016024688 @default.
• W2922146890 creator A5041301033 @default.
• W2922146890 creator A5080661583 @default.
• W2922146890 creator A5091370407 @default.
• W2922146890 date "2019-05-01" @default.
• W2922146890 modified "2023-10-16" @default.
• W2922146890 title "Learning Bayesian network parameters via minimax algorithm" @default.
• W2922146890 cites W1965555277 @default.
• W2922146890 cites W1970902974 @default.
• W2922146890 cites W1976775364 @default.
• W2922146890 cites W1978614948 @default.
• W2922146890 cites W1981367467 @default.
• W2922146890 cites W1987946334 @default.
• W2922146890 cites W1989926363 @default.
• W2922146890 cites W1993078297 @default.
• W2922146890 cites W2022655351 @default.
• W2922146890 cites W2047581137 @default.
• W2922146890 cites W2057393527 @default.
• W2922146890 cites W2064952440 @default.
• W2922146890 cites W2089831283 @default.
• W2922146890 cites W2096266885 @default.
• W2922146890 cites W2098173733 @default.
• W2922146890 cites W2102954194 @default.
• W2922146890 cites W2403438230 @default.
• W2922146890 cites W2751326998 @default.
• W2922146890 cites W4236354166 @default.
• W2922146890 doi "https://doi.org/10.1016/j.ijar.2019.03.001" @default.
• W2922146890 hasPublicationYear "2019" @default.
• W2922146890 type Work @default.
• W2922146890 sameAs 2922146890 @default.
• W2922146890 citedByCount "22" @default.
• W2922146890 countsByYear W29221468902019 @default.
• W2922146890 countsByYear W29221468902020 @default.
• W2922146890 countsByYear W29221468902021 @default.
• W2922146890 countsByYear W29221468902022 @default.
• W2922146890 countsByYear W29221468902023 @default.
• W2922146890 crossrefType "journal-article" @default.
• W2922146890 hasAuthorship W2922146890A5005364117 @default.
• W2922146890 hasAuthorship W2922146890A5011685930 @default.
• W2922146890 hasAuthorship W2922146890A5016024688 @default.
• W2922146890 hasAuthorship W2922146890A5041301033 @default.
• W2922146890 hasAuthorship W2922146890A5080661583 @default.
• W2922146890 hasAuthorship W2922146890A5091370407 @default.
• W2922146890 hasBestOaLocation W29221468901 @default.
• W2922146890 hasConcept C106301342 @default.
• W2922146890 hasConcept C107673813 @default.
• W2922146890 hasConcept C11413529 @default.
• W2922146890 hasConcept C119857082 @default.
• W2922146890 hasConcept C121332964 @default.
• W2922146890 hasConcept C126255220 @default.
• W2922146890 hasConcept C149728462 @default.
• W2922146890 hasConcept C154945302 @default.
• W2922146890 hasConcept C177769412 @default.
• W2922146890 hasConcept C22019652 @default.
• W2922146890 hasConcept C33923547 @default.
• W2922146890 hasConcept C41008148 @default.
• W2922146890 hasConcept C50644808 @default.
• W2922146890 hasConcept C57830394 @default.
• W2922146890 hasConcept C62520636 @default.
• W2922146890 hasConcept C9679016 @default.
• W2922146890 hasConceptScore W2922146890C106301342 @default.
• W2922146890 hasConceptScore W2922146890C107673813 @default.
• W2922146890 hasConceptScore W2922146890C11413529 @default.
• W2922146890 hasConceptScore W2922146890C119857082 @default.
• W2922146890 hasConceptScore W2922146890C121332964 @default.
• W2922146890 hasConceptScore W2922146890C126255220 @default.
• W2922146890 hasConceptScore W2922146890C149728462 @default.
• W2922146890 hasConceptScore W2922146890C154945302 @default.
• W2922146890 hasConceptScore W2922146890C177769412 @default.
• W2922146890 hasConceptScore W2922146890C22019652 @default.
• W2922146890 hasConceptScore W2922146890C33923547 @default.
• W2922146890 hasConceptScore W2922146890C41008148 @default.
• W2922146890 hasConceptScore W2922146890C50644808 @default.
• W2922146890 hasConceptScore W2922146890C57830394 @default.
• W2922146890 hasConceptScore W2922146890C62520636 @default.
• W2922146890 hasConceptScore W2922146890C9679016 @default.
• W2922146890 hasFunder F4320321001 @default.
• W2922146890 hasLocation W29221468901 @default.
• W2922146890 hasLocation W29221468902 @default.
• W2922146890 hasOpenAccess W2922146890 @default.
• W2922146890 hasPrimaryLocation W29221468901 @default.
• W2922146890 hasRelatedWork W2091694828 @default.
• W2922146890 hasRelatedWork W2093362081 @default.
• W2922146890 hasRelatedWork W2348047388 @default.
• W2922146890 hasRelatedWork W2922146890 @default.
• W2922146890 hasRelatedWork W2989932438 @default.
• W2922146890 hasRelatedWork W3000691203 @default.
• W2922146890 hasRelatedWork W3099765033 @default.
• W2922146890 hasRelatedWork W3121504630 @default.
• W2922146890 hasRelatedWork W4210794429 @default.
• W2922146890 hasRelatedWork W4287904950 @default.
• W2922146890 hasVolume "108" @default.
• W2922146890 isParatext "false" @default.
• W2922146890 isRetracted "false" @default.

• next