Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015549319> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3015549319 abstract "We investigate the problem of machine learning with mislabeled training data. We try to make the effects of mislabeled training better understood through analysis of the basic model and equations that characterize the problem. This includes results about the ability of the noisy model to make the same decisions as the clean model and the effects of noise on model performance. In addition to providing better insights we also are able to show that the Maximum Likelihood (ML) estimate of the parameters of the noisy model determine those of the clean model. This property is obtained through the use of the ML invariance property and leads to an approach to developing a classifier when training has been mislabeled: namely train the classifier on noisy data and adjust the decision threshold based on the noise levels and/or class priors. We show how our approach to mislabeled training works with multi-layered perceptrons (MLPs)." @default.
- W3015549319 created "2020-04-17" @default.
- W3015549319 creator A5022347882 @default.
- W3015549319 creator A5046467896 @default.
- W3015549319 creator A5047770365 @default.
- W3015549319 creator A5065713279 @default.
- W3015549319 creator A5067041166 @default.
- W3015549319 creator A5071977964 @default.
- W3015549319 date "2020-05-01" @default.
- W3015549319 modified "2023-09-23" @default.
- W3015549319 title "Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data" @default.
- W3015549319 cites W2105418482 @default.
- W3015549319 cites W2141253686 @default.
- W3015549319 cites W2167460663 @default.
- W3015549319 cites W2403681572 @default.
- W3015549319 doi "https://doi.org/10.1109/icassp40776.2020.9053014" @default.
- W3015549319 hasPublicationYear "2020" @default.
- W3015549319 type Work @default.
- W3015549319 sameAs 3015549319 @default.
- W3015549319 citedByCount "0" @default.
- W3015549319 crossrefType "proceedings-article" @default.
- W3015549319 hasAuthorship W3015549319A5022347882 @default.
- W3015549319 hasAuthorship W3015549319A5046467896 @default.
- W3015549319 hasAuthorship W3015549319A5047770365 @default.
- W3015549319 hasAuthorship W3015549319A5065713279 @default.
- W3015549319 hasAuthorship W3015549319A5067041166 @default.
- W3015549319 hasAuthorship W3015549319A5071977964 @default.
- W3015549319 hasBestOaLocation W30155493192 @default.
- W3015549319 hasConcept C107673813 @default.
- W3015549319 hasConcept C111472728 @default.
- W3015549319 hasConcept C115961682 @default.
- W3015549319 hasConcept C119857082 @default.
- W3015549319 hasConcept C121332964 @default.
- W3015549319 hasConcept C138885662 @default.
- W3015549319 hasConcept C153180895 @default.
- W3015549319 hasConcept C153294291 @default.
- W3015549319 hasConcept C154945302 @default.
- W3015549319 hasConcept C177769412 @default.
- W3015549319 hasConcept C189950617 @default.
- W3015549319 hasConcept C2777211547 @default.
- W3015549319 hasConcept C2781170535 @default.
- W3015549319 hasConcept C41008148 @default.
- W3015549319 hasConcept C50644808 @default.
- W3015549319 hasConcept C51632099 @default.
- W3015549319 hasConcept C60908668 @default.
- W3015549319 hasConcept C95623464 @default.
- W3015549319 hasConcept C99498987 @default.
- W3015549319 hasConceptScore W3015549319C107673813 @default.
- W3015549319 hasConceptScore W3015549319C111472728 @default.
- W3015549319 hasConceptScore W3015549319C115961682 @default.
- W3015549319 hasConceptScore W3015549319C119857082 @default.
- W3015549319 hasConceptScore W3015549319C121332964 @default.
- W3015549319 hasConceptScore W3015549319C138885662 @default.
- W3015549319 hasConceptScore W3015549319C153180895 @default.
- W3015549319 hasConceptScore W3015549319C153294291 @default.
- W3015549319 hasConceptScore W3015549319C154945302 @default.
- W3015549319 hasConceptScore W3015549319C177769412 @default.
- W3015549319 hasConceptScore W3015549319C189950617 @default.
- W3015549319 hasConceptScore W3015549319C2777211547 @default.
- W3015549319 hasConceptScore W3015549319C2781170535 @default.
- W3015549319 hasConceptScore W3015549319C41008148 @default.
- W3015549319 hasConceptScore W3015549319C50644808 @default.
- W3015549319 hasConceptScore W3015549319C51632099 @default.
- W3015549319 hasConceptScore W3015549319C60908668 @default.
- W3015549319 hasConceptScore W3015549319C95623464 @default.
- W3015549319 hasConceptScore W3015549319C99498987 @default.
- W3015549319 hasLocation W30155493191 @default.
- W3015549319 hasLocation W30155493192 @default.
- W3015549319 hasOpenAccess W3015549319 @default.
- W3015549319 hasPrimaryLocation W30155493191 @default.
- W3015549319 hasRelatedWork W10719664 @default.
- W3015549319 hasRelatedWork W10786582 @default.
- W3015549319 hasRelatedWork W11389402 @default.
- W3015549319 hasRelatedWork W13426584 @default.
- W3015549319 hasRelatedWork W3540334 @default.
- W3015549319 hasRelatedWork W6680660 @default.
- W3015549319 hasRelatedWork W6770330 @default.
- W3015549319 hasRelatedWork W6869908 @default.
- W3015549319 hasRelatedWork W7655147 @default.
- W3015549319 hasRelatedWork W8657122 @default.
- W3015549319 isParatext "false" @default.
- W3015549319 isRetracted "false" @default.
- W3015549319 magId "3015549319" @default.
- W3015549319 workType "article" @default.