Matches in SemOpenAlex for { <https://semopenalex.org/work/W2070702960> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2070702960 endingPage "1841" @default.
- W2070702960 startingPage "1828" @default.
- W2070702960 abstract "AdaBoost is a method to improve a given learning algorithm's classification accuracy by combining its hypotheses. Adaptivity, one of the significant advantages of AdaBoost, makes AdaBoost maximize the smallest margin so that AdaBoost has good generalization ability. However, when the samples with large negative margins are noisy or atypical, the maximized margin is actually a “hard margin.” The adaptive feature makes AdaBoost sensitive to the sampling fluctuations, and prone to overfitting. Therefore, the traditional schemes prevent AdaBoost from overfitting by heavily damping the influences of samples with large negative margins. However, the samples with large negative margins are not always noisy or atypical; thus, the traditional schemes of preventing overfitting may not be reasonable. In order to learn a classifier with high generalization performance and prevent overfitting, it is necessary to perform statistical analysis for the margins of training samples. Herein, Hoeffding inequality is adopted as a statistical tool to divide training samples into reliable samples and temporary unreliable samples. A new boosting algorithm, which is named DAdaBoost, is introduced to deal with reliable samples and temporary unreliable samples separately. Since DAdaBoost adjusts weighting scheme dynamically, the loss function of DAdaBoost is not fixed. In fact, it is a series of nonconvex functions that gradually approach the 0-1 function as the algorithm evolves. By defining a virtual classifier, the dynamic adjusted weighting scheme is well unified into the progress of DAdaBoost, and the upper bound of training error is deduced. The experiments on both synthetic and real world data show that DAdaBoost has many merits. Based on the experiments, we conclude that DAdaBoost can effectively prevent AdaBoost from overfitting." @default.
- W2070702960 created "2016-06-24" @default.
- W2070702960 creator A5055813170 @default.
- W2070702960 creator A5062005196 @default.
- W2070702960 creator A5078233601 @default.
- W2070702960 creator A5087186760 @default.
- W2070702960 date "2012-11-01" @default.
- W2070702960 modified "2023-10-16" @default.
- W2070702960 title "A Dynamic AdaBoost Algorithm With Adaptive Changes of Loss Function" @default.
- W2070702960 cites W1491053661 @default.
- W2070702960 cites W1540007258 @default.
- W2070702960 cites W1597529531 @default.
- W2070702960 cites W1968032964 @default.
- W2070702960 cites W1968969471 @default.
- W2070702960 cites W1975846642 @default.
- W2070702960 cites W1988790447 @default.
- W2070702960 cites W2023163512 @default.
- W2070702960 cites W2024046085 @default.
- W2070702960 cites W2035850120 @default.
- W2070702960 cites W2051570664 @default.
- W2070702960 cites W2063774093 @default.
- W2070702960 cites W2069928811 @default.
- W2070702960 cites W2076118331 @default.
- W2070702960 cites W2084362125 @default.
- W2070702960 cites W2115715186 @default.
- W2070702960 cites W2121043290 @default.
- W2070702960 cites W2123422288 @default.
- W2070702960 cites W2131533724 @default.
- W2070702960 cites W2142182456 @default.
- W2070702960 cites W2148611932 @default.
- W2070702960 cites W2150755264 @default.
- W2070702960 cites W4244952642 @default.
- W2070702960 cites W4254158956 @default.
- W2070702960 doi "https://doi.org/10.1109/tsmcc.2012.2227471" @default.
- W2070702960 hasPublicationYear "2012" @default.
- W2070702960 type Work @default.
- W2070702960 sameAs 2070702960 @default.
- W2070702960 citedByCount "7" @default.
- W2070702960 countsByYear W20707029602014 @default.
- W2070702960 countsByYear W20707029602015 @default.
- W2070702960 countsByYear W20707029602017 @default.
- W2070702960 countsByYear W20707029602023 @default.
- W2070702960 crossrefType "journal-article" @default.
- W2070702960 hasAuthorship W2070702960A5055813170 @default.
- W2070702960 hasAuthorship W2070702960A5062005196 @default.
- W2070702960 hasAuthorship W2070702960A5078233601 @default.
- W2070702960 hasAuthorship W2070702960A5087186760 @default.
- W2070702960 hasConcept C11413529 @default.
- W2070702960 hasConcept C119857082 @default.
- W2070702960 hasConcept C126838900 @default.
- W2070702960 hasConcept C141404830 @default.
- W2070702960 hasConcept C153180895 @default.
- W2070702960 hasConcept C154945302 @default.
- W2070702960 hasConcept C183115368 @default.
- W2070702960 hasConcept C22019652 @default.
- W2070702960 hasConcept C33923547 @default.
- W2070702960 hasConcept C41008148 @default.
- W2070702960 hasConcept C46686674 @default.
- W2070702960 hasConcept C50644808 @default.
- W2070702960 hasConcept C71924100 @default.
- W2070702960 hasConcept C774472 @default.
- W2070702960 hasConcept C95623464 @default.
- W2070702960 hasConceptScore W2070702960C11413529 @default.
- W2070702960 hasConceptScore W2070702960C119857082 @default.
- W2070702960 hasConceptScore W2070702960C126838900 @default.
- W2070702960 hasConceptScore W2070702960C141404830 @default.
- W2070702960 hasConceptScore W2070702960C153180895 @default.
- W2070702960 hasConceptScore W2070702960C154945302 @default.
- W2070702960 hasConceptScore W2070702960C183115368 @default.
- W2070702960 hasConceptScore W2070702960C22019652 @default.
- W2070702960 hasConceptScore W2070702960C33923547 @default.
- W2070702960 hasConceptScore W2070702960C41008148 @default.
- W2070702960 hasConceptScore W2070702960C46686674 @default.
- W2070702960 hasConceptScore W2070702960C50644808 @default.
- W2070702960 hasConceptScore W2070702960C71924100 @default.
- W2070702960 hasConceptScore W2070702960C774472 @default.
- W2070702960 hasConceptScore W2070702960C95623464 @default.
- W2070702960 hasIssue "6" @default.
- W2070702960 hasLocation W20707029601 @default.
- W2070702960 hasOpenAccess W2070702960 @default.
- W2070702960 hasPrimaryLocation W20707029601 @default.
- W2070702960 hasRelatedWork W1487831638 @default.
- W2070702960 hasRelatedWork W1602602470 @default.
- W2070702960 hasRelatedWork W1987859285 @default.
- W2070702960 hasRelatedWork W1996541855 @default.
- W2070702960 hasRelatedWork W2003125512 @default.
- W2070702960 hasRelatedWork W2028759454 @default.
- W2070702960 hasRelatedWork W2105310066 @default.
- W2070702960 hasRelatedWork W2742991909 @default.
- W2070702960 hasRelatedWork W2944309180 @default.
- W2070702960 hasRelatedWork W4381786038 @default.
- W2070702960 hasVolume "42" @default.
- W2070702960 isParatext "false" @default.
- W2070702960 isRetracted "false" @default.
- W2070702960 magId "2070702960" @default.
- W2070702960 workType "article" @default.