Matches in SemOpenAlex for { <https://semopenalex.org/work/W2790733271> ?p ?o ?g. }
- W2790733271 endingPage "142" @default.
- W2790733271 startingPage "128" @default.
- W2790733271 abstract "An extreme learning machine (ELM) is a popular analytic single hidden layer feedforward neural network because of its rapid learning capacity. However, vanilla dense ELMs are affected by the overfitting problem when the number of hidden neurons is high. Further direct consequences of the density are decreases in both the training and prediction speeds. In this study, we propose an incremental method for sparsifying the ELM using a newly devised indicator driven by the condition number in the ELM design matrix, in which we call sparse pseudoinverse incremental-ELM (SPI-ELM). SPI-ELM exhibits better generalization performance and lower run-time complexity compared with ELM. However, the sparsification process may negatively affect the learning speed of SPI-ELM; thus, we introduce an iterative matrix decomposition algorithm to address this issue. We also demonstrate that there is a useful relationship between the condition number in the ELM design matrix and the number of hidden neurons. This relationship helps to understand the random weights and nonlinear activation functions in ELMs. We evaluated the SPI-ELM method based on 20 benchmark data sets from the University of California Irvine repository and three real-world databases from the computer vision domain." @default.
- W2790733271 created "2018-03-29" @default.
- W2790733271 creator A5051093782 @default.
- W2790733271 creator A5051422395 @default.
- W2790733271 creator A5065415014 @default.
- W2790733271 date "2018-04-01" @default.
- W2790733271 modified "2023-10-16" @default.
- W2790733271 title "Sparse pseudoinverse incremental extreme learning machine" @default.
- W2790733271 cites W1116688463 @default.
- W2790733271 cites W1184550957 @default.
- W2790733271 cites W1977923618 @default.
- W2790733271 cites W1978736542 @default.
- W2790733271 cites W1980713635 @default.
- W2790733271 cites W1981252300 @default.
- W2790733271 cites W1987390907 @default.
- W2790733271 cites W2003912160 @default.
- W2790733271 cites W2016924348 @default.
- W2790733271 cites W2019607443 @default.
- W2790733271 cites W2019718627 @default.
- W2790733271 cites W2026131661 @default.
- W2790733271 cites W2027792236 @default.
- W2790733271 cites W2028759731 @default.
- W2790733271 cites W2029200918 @default.
- W2790733271 cites W2038235550 @default.
- W2790733271 cites W2038860231 @default.
- W2790733271 cites W2040647667 @default.
- W2790733271 cites W2047431064 @default.
- W2790733271 cites W2096987757 @default.
- W2790733271 cites W2097021318 @default.
- W2790733271 cites W2111072639 @default.
- W2790733271 cites W2122040390 @default.
- W2790733271 cites W2130378394 @default.
- W2790733271 cites W2141695047 @default.
- W2790733271 cites W2170078634 @default.
- W2790733271 cites W2195569869 @default.
- W2790733271 cites W2234781454 @default.
- W2790733271 cites W2263756804 @default.
- W2790733271 cites W2464262491 @default.
- W2790733271 cites W2561944084 @default.
- W2790733271 cites W310542863 @default.
- W2790733271 doi "https://doi.org/10.1016/j.neucom.2018.01.087" @default.
- W2790733271 hasPublicationYear "2018" @default.
- W2790733271 type Work @default.
- W2790733271 sameAs 2790733271 @default.
- W2790733271 citedByCount "16" @default.
- W2790733271 countsByYear W27907332712018 @default.
- W2790733271 countsByYear W27907332712019 @default.
- W2790733271 countsByYear W27907332712020 @default.
- W2790733271 countsByYear W27907332712021 @default.
- W2790733271 countsByYear W27907332712022 @default.
- W2790733271 crossrefType "journal-article" @default.
- W2790733271 hasAuthorship W2790733271A5051093782 @default.
- W2790733271 hasAuthorship W2790733271A5051422395 @default.
- W2790733271 hasAuthorship W2790733271A5065415014 @default.
- W2790733271 hasConcept C106487976 @default.
- W2790733271 hasConcept C11413529 @default.
- W2790733271 hasConcept C119857082 @default.
- W2790733271 hasConcept C127413603 @default.
- W2790733271 hasConcept C13280743 @default.
- W2790733271 hasConcept C133731056 @default.
- W2790733271 hasConcept C134306372 @default.
- W2790733271 hasConcept C153180895 @default.
- W2790733271 hasConcept C154945302 @default.
- W2790733271 hasConcept C159985019 @default.
- W2790733271 hasConcept C177148314 @default.
- W2790733271 hasConcept C185798385 @default.
- W2790733271 hasConcept C192562407 @default.
- W2790733271 hasConcept C205649164 @default.
- W2790733271 hasConcept C207467116 @default.
- W2790733271 hasConcept C21556879 @default.
- W2790733271 hasConcept C22019652 @default.
- W2790733271 hasConcept C2524010 @default.
- W2790733271 hasConcept C2780150128 @default.
- W2790733271 hasConcept C33923547 @default.
- W2790733271 hasConcept C38858127 @default.
- W2790733271 hasConcept C41008148 @default.
- W2790733271 hasConcept C47702885 @default.
- W2790733271 hasConcept C50644808 @default.
- W2790733271 hasConceptScore W2790733271C106487976 @default.
- W2790733271 hasConceptScore W2790733271C11413529 @default.
- W2790733271 hasConceptScore W2790733271C119857082 @default.
- W2790733271 hasConceptScore W2790733271C127413603 @default.
- W2790733271 hasConceptScore W2790733271C13280743 @default.
- W2790733271 hasConceptScore W2790733271C133731056 @default.
- W2790733271 hasConceptScore W2790733271C134306372 @default.
- W2790733271 hasConceptScore W2790733271C153180895 @default.
- W2790733271 hasConceptScore W2790733271C154945302 @default.
- W2790733271 hasConceptScore W2790733271C159985019 @default.
- W2790733271 hasConceptScore W2790733271C177148314 @default.
- W2790733271 hasConceptScore W2790733271C185798385 @default.
- W2790733271 hasConceptScore W2790733271C192562407 @default.
- W2790733271 hasConceptScore W2790733271C205649164 @default.
- W2790733271 hasConceptScore W2790733271C207467116 @default.
- W2790733271 hasConceptScore W2790733271C21556879 @default.
- W2790733271 hasConceptScore W2790733271C22019652 @default.
- W2790733271 hasConceptScore W2790733271C2524010 @default.
- W2790733271 hasConceptScore W2790733271C2780150128 @default.
- W2790733271 hasConceptScore W2790733271C33923547 @default.