FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383566847> ?p ?o ?g. }

• W4383566847 endingPage "214" @default.
• W4383566847 startingPage "201" @default.
• W4383566847 abstract "The extreme learning machine (ELM) is a form of single-layer feed-forward neural network. It has recently garnered much attention from scholars and academics due to its ability for rapid model training and development as well as its respectable generalization potential. However, irrespective of these advantages, there remains a great difficulty in modeling real-world applications with the ELM model. Real data sets encountered in practice often contain a heteroscedastic nature, which can result in an unreliable ELM model with a poor predictive capacity. In order to address this shortfall in the application of ELM models, this chapter will seek to present several ELM-based methodologies which are capable of handling such variation in the data sets. To begin the chapter, a brief review of the ELM technique, as well as its advantages and disadvantages (the reader is directed to Chapter 4 for a more detailed discussion of advantages and disadvantages), is presented. Following this, the mathematical formulation of MATLAB programming is presented in complete detail for four ELM-based models, including (1) classical ELM, (2) regularized ELM, (3) weighted regularized ELM, (4) outlier-robust ELM." @default.
• W4383566847 created "2023-07-08" @default.
• W4383566847 creator A5066692423 @default.
• W4383566847 creator A5074154240 @default.
• W4383566847 creator A5086247042 @default.
• W4383566847 date "2023-01-01" @default.
• W4383566847 modified "2023-10-17" @default.
• W4383566847 title "Outlier-based models of the non-tuned neural network—concept" @default.
• W4383566847 cites W1974788546 @default.
• W4383566847 cites W1978996791 @default.
• W4383566847 cites W1986096622 @default.
• W4383566847 cites W2024410299 @default.
• W4383566847 cites W2026131661 @default.
• W4383566847 cites W2050834445 @default.
• W4383566847 cites W2070253211 @default.
• W4383566847 cites W2098012923 @default.
• W4383566847 cites W2101674911 @default.
• W4383566847 cites W2107861471 @default.
• W4383566847 cites W2111072639 @default.
• W4383566847 cites W2133042373 @default.
• W4383566847 cites W2134603844 @default.
• W4383566847 cites W21410603 @default.
• W4383566847 cites W2145962650 @default.
• W4383566847 cites W2154852616 @default.
• W4383566847 cites W2313350192 @default.
• W4383566847 cites W2559671849 @default.
• W4383566847 cites W2588898025 @default.
• W4383566847 cites W2595291109 @default.
• W4383566847 cites W2596154889 @default.
• W4383566847 cites W2753179649 @default.
• W4383566847 cites W2754332904 @default.
• W4383566847 cites W2784239585 @default.
• W4383566847 cites W2803907192 @default.
• W4383566847 cites W2885114451 @default.
• W4383566847 cites W2886116972 @default.
• W4383566847 cites W2891787367 @default.
• W4383566847 cites W2917316030 @default.
• W4383566847 cites W2917788105 @default.
• W4383566847 cites W2920794465 @default.
• W4383566847 cites W2931813856 @default.
• W4383566847 cites W2935484715 @default.
• W4383566847 cites W2945633508 @default.
• W4383566847 cites W2948700797 @default.
• W4383566847 cites W2949483514 @default.
• W4383566847 cites W2969357546 @default.
• W4383566847 cites W2981897990 @default.
• W4383566847 cites W2996066241 @default.
• W4383566847 cites W2998745260 @default.
• W4383566847 cites W3002212774 @default.
• W4383566847 cites W3013631219 @default.
• W4383566847 cites W3125247167 @default.
• W4383566847 cites W3154995314 @default.
• W4383566847 cites W3184903247 @default.
• W4383566847 cites W4250955649 @default.
• W4383566847 cites W4307483271 @default.
• W4383566847 doi "https://doi.org/10.1016/b978-0-443-15284-9.00008-2" @default.
• W4383566847 hasPublicationYear "2023" @default.
• W4383566847 type Work @default.
• W4383566847 citedByCount "0" @default.
• W4383566847 crossrefType "book-chapter" @default.
• W4383566847 hasAuthorship W4383566847A5066692423 @default.
• W4383566847 hasAuthorship W4383566847A5074154240 @default.
• W4383566847 hasAuthorship W4383566847A5086247042 @default.
• W4383566847 hasConcept C111919701 @default.
• W4383566847 hasConcept C119857082 @default.
• W4383566847 hasConcept C134306372 @default.
• W4383566847 hasConcept C154945302 @default.
• W4383566847 hasConcept C177148314 @default.
• W4383566847 hasConcept C2780150128 @default.
• W4383566847 hasConcept C2780365114 @default.
• W4383566847 hasConcept C33923547 @default.
• W4383566847 hasConcept C41008148 @default.
• W4383566847 hasConcept C50644808 @default.
• W4383566847 hasConcept C79337645 @default.
• W4383566847 hasConceptScore W4383566847C111919701 @default.
• W4383566847 hasConceptScore W4383566847C119857082 @default.
• W4383566847 hasConceptScore W4383566847C134306372 @default.
• W4383566847 hasConceptScore W4383566847C154945302 @default.
• W4383566847 hasConceptScore W4383566847C177148314 @default.
• W4383566847 hasConceptScore W4383566847C2780150128 @default.
• W4383566847 hasConceptScore W4383566847C2780365114 @default.
• W4383566847 hasConceptScore W4383566847C33923547 @default.
• W4383566847 hasConceptScore W4383566847C41008148 @default.
• W4383566847 hasConceptScore W4383566847C50644808 @default.
• W4383566847 hasConceptScore W4383566847C79337645 @default.
• W4383566847 hasLocation W43835668471 @default.
• W4383566847 hasOpenAccess W4383566847 @default.
• W4383566847 hasPrimaryLocation W43835668471 @default.
• W4383566847 hasRelatedWork W1525510058 @default.
• W4383566847 hasRelatedWork W1545807863 @default.
• W4383566847 hasRelatedWork W2005318905 @default.
• W4383566847 hasRelatedWork W2086369498 @default.
• W4383566847 hasRelatedWork W2475251269 @default.
• W4383566847 hasRelatedWork W2945765785 @default.
• W4383566847 hasRelatedWork W2969890106 @default.
• W4383566847 hasRelatedWork W3127430868 @default.
• W4383566847 hasRelatedWork W3134233996 @default.
• W4383566847 hasRelatedWork W3185179407 @default.

• next