Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132532743> ?p ?o ?g. }
- W3132532743 endingPage "14" @default.
- W3132532743 startingPage "1" @default.
- W3132532743 abstract "Extreme Learning Machine (ELM) as a fast and efficient neural network model in pattern recognition and machine learning will decline when the labeled training sample is insufficient. Transfer learning helps the target task to learn a reliable model by using plentiful labeled samples from the different but relevant domain. In this paper, we propose a supervised Extreme Learning Machine with knowledge transferability, called Transfer Extreme Learning Machine with Output Weight Alignment (TELM-OWA). Firstly, it reduces the distribution difference between domains by aligning the output weight matrix of the ELM trained by the labeled samples from the source and target domains. Secondly, the approximation between the interdomain ELM output weight matrix is added to the objective function to further realize the cross-domain transfer of knowledge. Thirdly, we consider the objective function as the least square problem and transform it into a standard ELM model to be efficiently solved. Finally, the effectiveness of the proposed algorithm is verified by classification experiments on 16 sets of image datasets and 6 sets of text datasets, and the result demonstrates the competitive performance of our method with respect to other ELM models and transfer learning approach." @default.
- W3132532743 created "2021-03-01" @default.
- W3132532743 creator A5000868256 @default.
- W3132532743 creator A5007301470 @default.
- W3132532743 creator A5012528047 @default.
- W3132532743 creator A5037667256 @default.
- W3132532743 date "2021-02-12" @default.
- W3132532743 modified "2023-10-17" @default.
- W3132532743 title "Transfer Extreme Learning Machine with Output Weight Alignment" @default.
- W3132532743 cites W1439842103 @default.
- W3132532743 cites W1977678056 @default.
- W3132532743 cites W1980084379 @default.
- W3132532743 cites W1980713635 @default.
- W3132532743 cites W2010425280 @default.
- W3132532743 cites W2021006603 @default.
- W3132532743 cites W2042184006 @default.
- W3132532743 cites W2059477850 @default.
- W3132532743 cites W2067443264 @default.
- W3132532743 cites W2078578402 @default.
- W3132532743 cites W2078622091 @default.
- W3132532743 cites W2096943734 @default.
- W3132532743 cites W2096987757 @default.
- W3132532743 cites W2100664256 @default.
- W3132532743 cites W2104068492 @default.
- W3132532743 cites W2111072639 @default.
- W3132532743 cites W2115403315 @default.
- W3132532743 cites W2138260443 @default.
- W3132532743 cites W2140224582 @default.
- W3132532743 cites W2149466042 @default.
- W3132532743 cites W2162854380 @default.
- W3132532743 cites W2164943005 @default.
- W3132532743 cites W2165698076 @default.
- W3132532743 cites W2410121489 @default.
- W3132532743 cites W2422365436 @default.
- W3132532743 cites W2507929878 @default.
- W3132532743 cites W2586833865 @default.
- W3132532743 cites W2775259072 @default.
- W3132532743 cites W2786589258 @default.
- W3132532743 cites W2787261406 @default.
- W3132532743 cites W2790025164 @default.
- W3132532743 cites W2798199013 @default.
- W3132532743 cites W2808007932 @default.
- W3132532743 cites W2895717704 @default.
- W3132532743 cites W2914885136 @default.
- W3132532743 cites W2924231817 @default.
- W3132532743 cites W2948279919 @default.
- W3132532743 cites W2953675148 @default.
- W3132532743 cites W2964285681 @default.
- W3132532743 cites W2966586610 @default.
- W3132532743 cites W2979509742 @default.
- W3132532743 cites W2991150929 @default.
- W3132532743 cites W3039883906 @default.
- W3132532743 cites W3045675141 @default.
- W3132532743 cites W3105479267 @default.
- W3132532743 cites W38577652 @default.
- W3132532743 doi "https://doi.org/10.1155/2021/6627765" @default.
- W3132532743 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7895561" @default.
- W3132532743 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33628212" @default.
- W3132532743 hasPublicationYear "2021" @default.
- W3132532743 type Work @default.
- W3132532743 sameAs 3132532743 @default.
- W3132532743 citedByCount "5" @default.
- W3132532743 countsByYear W31325327432022 @default.
- W3132532743 countsByYear W31325327432023 @default.
- W3132532743 crossrefType "journal-article" @default.
- W3132532743 hasAuthorship W3132532743A5000868256 @default.
- W3132532743 hasAuthorship W3132532743A5007301470 @default.
- W3132532743 hasAuthorship W3132532743A5012528047 @default.
- W3132532743 hasAuthorship W3132532743A5037667256 @default.
- W3132532743 hasBestOaLocation W31325327431 @default.
- W3132532743 hasConcept C106487976 @default.
- W3132532743 hasConcept C119857082 @default.
- W3132532743 hasConcept C127413603 @default.
- W3132532743 hasConcept C134306372 @default.
- W3132532743 hasConcept C14036430 @default.
- W3132532743 hasConcept C150899416 @default.
- W3132532743 hasConcept C153180895 @default.
- W3132532743 hasConcept C154945302 @default.
- W3132532743 hasConcept C159985019 @default.
- W3132532743 hasConcept C185592680 @default.
- W3132532743 hasConcept C192562407 @default.
- W3132532743 hasConcept C198531522 @default.
- W3132532743 hasConcept C201995342 @default.
- W3132532743 hasConcept C2780150128 @default.
- W3132532743 hasConcept C2780451532 @default.
- W3132532743 hasConcept C28006648 @default.
- W3132532743 hasConcept C33923547 @default.
- W3132532743 hasConcept C36503486 @default.
- W3132532743 hasConcept C41008148 @default.
- W3132532743 hasConcept C43617362 @default.
- W3132532743 hasConcept C50644808 @default.
- W3132532743 hasConcept C78458016 @default.
- W3132532743 hasConcept C86803240 @default.
- W3132532743 hasConceptScore W3132532743C106487976 @default.
- W3132532743 hasConceptScore W3132532743C119857082 @default.
- W3132532743 hasConceptScore W3132532743C127413603 @default.
- W3132532743 hasConceptScore W3132532743C134306372 @default.
- W3132532743 hasConceptScore W3132532743C14036430 @default.