FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366496922> ?p ?o ?g. }

• W4366496922 endingPage "66" @default.
• W4366496922 startingPage "49" @default.
• W4366496922 abstract "Ensuring the prediction accuracy of a learning algorithm on a theoretical basis is crucial and necessary for building the reliability of the learning algorithm. This paper analyzes prediction error obtained through the least square estimation in the generalized extreme learning machine (GELM), which applies the limiting behavior of the Moore-Penrose generalized inverse (M-P GI) to the output matrix of ELM. ELM is the random vector functional link (RVFL) network without direct input to output links Specifically, we analyze tail probabilities associated with upper and lower bounds to the error expressed by norms. The analysis employs the concepts of the L2 norm, the Frobenius norm, the stable rank, and the M-P GI. The coverage of theoretical analysis extends to the RVFL network. In addition, a criterion for more precise bounds of prediction errors that may give stochastically better network environments is provided. The analysis is applied to simple examples and large-size datasets to illustrate the procedure and verify the analysis and execution speed with big data. Based on this study, we can immediately obtain the upper and lower bounds of prediction errors and their associated tail probabilities through matrices calculations appearing in the GELM and RVFL. This analysis provides criteria for the reliability of the learning performance of a network in real-time and for network structure that enables obtaining better performance reliability. This analysis can be applied in various areas where the ELM and RVFL are adopted. The proposed analytical method will guide the theoretical analysis of errors occurring in DNNs, which employ a gradient descent algorithm." @default.
• W4366496922 created "2023-04-22" @default.
• W4366496922 creator A5046500483 @default.
• W4366496922 date "2023-07-01" @default.
• W4366496922 modified "2023-09-29" @default.
• W4366496922 title "Theoretical bounds of generalization error for generalized extreme learning machine and random vector functional link network" @default.
• W4366496922 cites W1202743199 @default.
• W4366496922 cites W1628829797 @default.
• W4366496922 cites W196871588 @default.
• W4366496922 cites W1996640396 @default.
• W4366496922 cites W1998058722 @default.
• W4366496922 cites W2026131661 @default.
• W4366496922 cites W2046907549 @default.
• W4366496922 cites W2071824193 @default.
• W4366496922 cites W2092317945 @default.
• W4366496922 cites W2099940443 @default.
• W4366496922 cites W2106447856 @default.
• W4366496922 cites W2136602355 @default.
• W4366496922 cites W2154952480 @default.
• W4366496922 cites W2158581396 @default.
• W4366496922 cites W2197173055 @default.
• W4366496922 cites W2434671519 @default.
• W4366496922 cites W2566079294 @default.
• W4366496922 cites W2619799366 @default.
• W4366496922 cites W2734205292 @default.
• W4366496922 cites W2744818200 @default.
• W4366496922 cites W2761362383 @default.
• W4366496922 cites W2775043420 @default.
• W4366496922 cites W2804648164 @default.
• W4366496922 cites W2905485021 @default.
• W4366496922 cites W2979452771 @default.
• W4366496922 cites W2981932139 @default.
• W4366496922 cites W2996149946 @default.
• W4366496922 cites W3022073510 @default.
• W4366496922 cites W3024982789 @default.
• W4366496922 cites W3100231902 @default.
• W4366496922 cites W3133541856 @default.
• W4366496922 cites W3199979266 @default.
• W4366496922 cites W4214615183 @default.
• W4366496922 cites W4221167690 @default.
• W4366496922 cites W4223612401 @default.
• W4366496922 cites W4238284510 @default.
• W4366496922 cites W4280499264 @default.
• W4366496922 cites W4292340316 @default.
• W4366496922 doi "https://doi.org/10.1016/j.neunet.2023.04.014" @default.
• W4366496922 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37146449" @default.
• W4366496922 hasPublicationYear "2023" @default.
• W4366496922 type Work @default.
• W4366496922 citedByCount "1" @default.
• W4366496922 countsByYear W43664969222023 @default.
• W4366496922 crossrefType "journal-article" @default.
• W4366496922 hasAuthorship W4366496922A5046500483 @default.
• W4366496922 hasConcept C105795698 @default.
• W4366496922 hasConcept C106487976 @default.
• W4366496922 hasConcept C11413529 @default.
• W4366496922 hasConcept C114614502 @default.
• W4366496922 hasConcept C121332964 @default.
• W4366496922 hasConcept C122123141 @default.
• W4366496922 hasConcept C12267149 @default.
• W4366496922 hasConcept C134306372 @default.
• W4366496922 hasConcept C138405894 @default.
• W4366496922 hasConcept C154945302 @default.
• W4366496922 hasConcept C158693339 @default.
• W4366496922 hasConcept C159985019 @default.
• W4366496922 hasConcept C163258240 @default.
• W4366496922 hasConcept C164226766 @default.
• W4366496922 hasConcept C177148314 @default.
• W4366496922 hasConcept C192562407 @default.
• W4366496922 hasConcept C207467116 @default.
• W4366496922 hasConcept C21556879 @default.
• W4366496922 hasConcept C2524010 @default.
• W4366496922 hasConcept C2779915298 @default.
• W4366496922 hasConcept C2780150128 @default.
• W4366496922 hasConcept C33923547 @default.
• W4366496922 hasConcept C41008148 @default.
• W4366496922 hasConcept C43214815 @default.
• W4366496922 hasConcept C50644808 @default.
• W4366496922 hasConcept C5465570 @default.
• W4366496922 hasConcept C62520636 @default.
• W4366496922 hasConcept C77553402 @default.
• W4366496922 hasConcept C92207270 @default.
• W4366496922 hasConceptScore W4366496922C105795698 @default.
• W4366496922 hasConceptScore W4366496922C106487976 @default.
• W4366496922 hasConceptScore W4366496922C11413529 @default.
• W4366496922 hasConceptScore W4366496922C114614502 @default.
• W4366496922 hasConceptScore W4366496922C121332964 @default.
• W4366496922 hasConceptScore W4366496922C122123141 @default.
• W4366496922 hasConceptScore W4366496922C12267149 @default.
• W4366496922 hasConceptScore W4366496922C134306372 @default.
• W4366496922 hasConceptScore W4366496922C138405894 @default.
• W4366496922 hasConceptScore W4366496922C154945302 @default.
• W4366496922 hasConceptScore W4366496922C158693339 @default.
• W4366496922 hasConceptScore W4366496922C159985019 @default.
• W4366496922 hasConceptScore W4366496922C163258240 @default.
• W4366496922 hasConceptScore W4366496922C164226766 @default.
• W4366496922 hasConceptScore W4366496922C177148314 @default.
• W4366496922 hasConceptScore W4366496922C192562407 @default.
• W4366496922 hasConceptScore W4366496922C207467116 @default.

• next