Adaptive multilayer extreme learning machines

Simple item page
dc.check.date2026-12-12en
dc.check.infoAccess to this article is restricted until 24 months after publication by request of the publisheren
dc.contributor.authorFilelis-Papadopoulos, Christos K.en
dc.contributor.authorMorrison, John P.en
dc.contributor.authorO’Reilly, Philipen
dc.contributor.funderScience Foundation Irelanden
dc.date.accessioned2025-01-15T16:21:02Z
dc.date.available2025-01-15T16:21:02Z
dc.date.issued2024-12-12en
dc.description.abstractExtreme learning machines is a neural network type that has been utilized in tasks such as regression and classification, due to their efficient training process, which is based on pseudoinverse matrices and randomized weights, avoiding the computationally intensive backpropagation. In order to further improve their performance and reduce their complexity with respect to number of required hyperparameters, especially in the case of multiple layer architectures, a novel multilayer adaptive approach, based on residual networks, is proposed. This approach constructs the network iteratively with respect to error minimization and parsimony using a recursive pseudoinverse matrix framework. A new block approach, using mixed precision arithmetic and Graphics Processing Units (GPU) is proposed. The proposed technique is coupled with a new adaptive penalty criterion to ensure adequate numbers of neurons are included in each layer, while avoiding highly correlated basis. Adaptive regularization, along with scaling, is also incorporated to ensure Symmetric Positive Definiteness (SPD) of the Gram matrix. Several random number distributions for the proposed approach are examined and discussed. Handling of large datasets is discussed and a new batch variant is proposed. The proposed scheme is evaluated for regression and classification tasks in a multitude of datasets and is compared with other neural network architectures.en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationFilelis-Papadopoulos, C. K., Morrison, J. P. and O’Reilly, P. (2024) 'Adaptive multilayer extreme learning machines', Mathematics and Computers in Simulation, 231, pp.71-98. https://doi.org/10.1016/j.matcom.2024.12.004en
dc.identifier.doihttps://doi.org/10.1016/j.matcom.2024.12.004en
dc.identifier.endpage98en
dc.identifier.issn0378-4754en
dc.identifier.journaltitleMathematics and Computers in Simulationen
dc.identifier.startpage71en
dc.identifier.urihttps://hdl.handle.net/10468/16835
dc.identifier.volume231en
dc.language.isoenen
dc.publisherElsevier Ltd.en
dc.relation.ispartofMathematics and Computers in Simulationen
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Strategic Partnership Programme/18/SPP/3459/IE/Next Generation Financial Services Technology (FINTECHNEXT)/en
dc.rights© 2024, International Association for Mathematics and Computers in Simulation (IMACS). Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.en
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectRecursive pseudoinverse matrixen
dc.subjectModelingen
dc.subjectMultilayer Extreme Learning Machineen
dc.subjectGraphics Processing Uniten
dc.titleAdaptive multilayer extreme learning machinesen
dc.typeArticle (peer-reviewed)en
oaire.citation.volume231en
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Adaptive_Neural_Network_R1_clean.pdf
Size:
1.42 MB
Format:
Adobe Portable Document Format
Description:
Accepted Version
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Journal Articles
Cork University Business School - Journal Articles