Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912162873> ?p ?o ?g. }
- W2912162873 endingPage "97" @default.
- W2912162873 startingPage "85" @default.
- W2912162873 abstract "With the direct input–output connections, a random vector functional link (RVFL) network is a simple and effective learning algorithm for single-hidden layer feedforward neural networks (SLFNs). RVFL is a universal approximator for continuous functions on compact sets with fast learning property. Owing to its simplicity and effectiveness, RVFL has attracted significant interest in numerous real-world applications. In reality, the performance of RVFL is often challenged by randomly assigned network parameters. In this paper, we propose a novel unsupervised network parameter learning method for RVFL, named sparse pre-trained random vector functional link (SP-RVFL for short) network. The proposed SP-RVFL uses a sparse autoencoder with ℓ1-norm regularization to adaptively learn superior network parameters for specific learning tasks. By doing so, the learned network parameters in SP-RVFL are embedded with the valuable information of input data, which alleviate the randomly generated parameter issue and improve the algorithmic performance. Experiments and comparisons on 16 diverse benchmarks from different domains confirm the effectiveness of the proposed SP-RVFL. The corresponding results also demonstrate that RVFL outperforms extreme learning machine (ELM)." @default.
- W2912162873 created "2019-02-21" @default.
- W2912162873 creator A5007475662 @default.
- W2912162873 creator A5036357902 @default.
- W2912162873 creator A5038549098 @default.
- W2912162873 creator A5038861185 @default.
- W2912162873 creator A5060042752 @default.
- W2912162873 date "2019-04-01" @default.
- W2912162873 modified "2023-10-18" @default.
- W2912162873 title "An unsupervised parameter learning model for RVFL neural network" @default.
- W2912162873 cites W1181113747 @default.
- W2912162873 cites W1498436455 @default.
- W2912162873 cites W1581984155 @default.
- W2912162873 cites W1644402181 @default.
- W2912162873 cites W1912982817 @default.
- W2912162873 cites W1963616278 @default.
- W2912162873 cites W1967675628 @default.
- W2912162873 cites W1980713635 @default.
- W2912162873 cites W1989131932 @default.
- W2912162873 cites W1996640396 @default.
- W2912162873 cites W2010755682 @default.
- W2912162873 cites W2021150359 @default.
- W2912162873 cites W2026131661 @default.
- W2912162873 cites W2042184006 @default.
- W2912162873 cites W2049292654 @default.
- W2912162873 cites W2083196737 @default.
- W2912162873 cites W2084251795 @default.
- W2912162873 cites W2100495367 @default.
- W2912162873 cites W2100556411 @default.
- W2912162873 cites W2126099446 @default.
- W2912162873 cites W2136922672 @default.
- W2912162873 cites W2138260443 @default.
- W2912162873 cites W2138383519 @default.
- W2912162873 cites W2140224582 @default.
- W2912162873 cites W2142224912 @default.
- W2912162873 cites W2146713522 @default.
- W2912162873 cites W2229668941 @default.
- W2912162873 cites W2286961399 @default.
- W2912162873 cites W2301541953 @default.
- W2912162873 cites W2346421499 @default.
- W2912162873 cites W2408701322 @default.
- W2912162873 cites W2463468632 @default.
- W2912162873 cites W2514029627 @default.
- W2912162873 cites W2590661630 @default.
- W2912162873 cites W2592311268 @default.
- W2912162873 cites W2607586284 @default.
- W2912162873 cites W2736488765 @default.
- W2912162873 cites W2743316100 @default.
- W2912162873 cites W2754747508 @default.
- W2912162873 cites W2762341992 @default.
- W2912162873 cites W2762962020 @default.
- W2912162873 cites W2792578766 @default.
- W2912162873 cites W2884713347 @default.
- W2912162873 cites W747162797 @default.
- W2912162873 doi "https://doi.org/10.1016/j.neunet.2019.01.007" @default.
- W2912162873 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30771727" @default.
- W2912162873 hasPublicationYear "2019" @default.
- W2912162873 type Work @default.
- W2912162873 sameAs 2912162873 @default.
- W2912162873 citedByCount "89" @default.
- W2912162873 countsByYear W29121628732019 @default.
- W2912162873 countsByYear W29121628732020 @default.
- W2912162873 countsByYear W29121628732021 @default.
- W2912162873 countsByYear W29121628732022 @default.
- W2912162873 countsByYear W29121628732023 @default.
- W2912162873 crossrefType "journal-article" @default.
- W2912162873 hasAuthorship W2912162873A5007475662 @default.
- W2912162873 hasAuthorship W2912162873A5036357902 @default.
- W2912162873 hasAuthorship W2912162873A5038549098 @default.
- W2912162873 hasAuthorship W2912162873A5038861185 @default.
- W2912162873 hasAuthorship W2912162873A5060042752 @default.
- W2912162873 hasConcept C101738243 @default.
- W2912162873 hasConcept C108583219 @default.
- W2912162873 hasConcept C11413529 @default.
- W2912162873 hasConcept C119857082 @default.
- W2912162873 hasConcept C154945302 @default.
- W2912162873 hasConcept C2776135515 @default.
- W2912162873 hasConcept C2780150128 @default.
- W2912162873 hasConcept C41008148 @default.
- W2912162873 hasConcept C50644808 @default.
- W2912162873 hasConceptScore W2912162873C101738243 @default.
- W2912162873 hasConceptScore W2912162873C108583219 @default.
- W2912162873 hasConceptScore W2912162873C11413529 @default.
- W2912162873 hasConceptScore W2912162873C119857082 @default.
- W2912162873 hasConceptScore W2912162873C154945302 @default.
- W2912162873 hasConceptScore W2912162873C2776135515 @default.
- W2912162873 hasConceptScore W2912162873C2780150128 @default.
- W2912162873 hasConceptScore W2912162873C41008148 @default.
- W2912162873 hasConceptScore W2912162873C50644808 @default.
- W2912162873 hasFunder F4320321001 @default.
- W2912162873 hasFunder F4320322186 @default.
- W2912162873 hasFunder F4320322725 @default.
- W2912162873 hasLocation W29121628731 @default.
- W2912162873 hasLocation W29121628732 @default.
- W2912162873 hasOpenAccess W2912162873 @default.
- W2912162873 hasPrimaryLocation W29121628731 @default.
- W2912162873 hasRelatedWork W2669956259 @default.
- W2912162873 hasRelatedWork W2939353110 @default.