Näytä suppeat kuvailutiedot

dc.contributor.authorKärkkäinen, Tommi
dc.date.accessioned2019-02-11T11:17:52Z
dc.date.available2019-02-11T11:17:52Z
dc.date.issued2018
dc.identifier.citationKärkkäinen, T. (2018). Extreme Minimal Learning Machine. In <i>ESANN 2018 : Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning</i> (pp. 237-242). ESANN. <a href="https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2018-72.pdf" target="_blank">https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2018-72.pdf</a>
dc.identifier.otherCONVID_28889038
dc.identifier.otherTUTKAID_80471
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/62746
dc.description.abstractExtreme Learning Machine (ELM) and Minimal Learning Machine (MLM) are nonlinear and scalable machine learning techniques with randomly generated basis. Both techniques share a step where a matrix of weights for the linear combination of the basis is recovered. In MLM, the kernel in this step corresponds to distance calculations between the training data and a set of reference points, whereas in ELM transformation with a sigmoidal activation function is most commonly used. MLM then needs additional interpolation step to estimate the actual distance-regression based output. A natural combination of these two techniques is proposed here, i.e., to use a distance-based kernel characteristic in MLM in ELM. The experimental results show promising potential of the proposed technique.Extreme Learning Machine (ELM) and Minimal Learning Machine (MLM) are nonlinear and scalable machine learning techniques with randomly generated basis. Both techniques share a step where a matrix of weights for the linear combination of the basis is recovered. In MLM, the kernel in this step corresponds to distance calculations between the training data and a set of reference points, whereas in ELM transformation with a sigmoidal activation function is most commonly used. MLM then needs additional interpolation step to estimate the actual distance-regression based output. A natural combination of these two techniques is proposed here, i.e., to use a distance-based kernel characteristic in MLM in ELM. The experimental results show promising potential of the proposed technique.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherESANN
dc.relation.ispartofESANN 2018 : Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
dc.relation.urihttps://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2018-72.pdf
dc.rightsIn Copyright
dc.subject.otherExtreme Learning Machine
dc.subject.otherMinimal Learning Machine
dc.titleExtreme Minimal Learning Machine
dc.typeconferenceObject
dc.identifier.urnURN:NBN:fi:jyu-201901281316
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineTietotekniikkafi
dc.contributor.oppiaineMathematical Information Technologyen
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
dc.date.updated2019-01-28T07:15:14Z
dc.relation.isbn978-2-87587-047-6
dc.type.coarhttp://purl.org/coar/resource_type/c_5794
dc.description.reviewstatuspeerReviewed
dc.format.pagerange237-242
dc.type.versionpublishedVersion
dc.rights.copyright© Author, 2018
dc.rights.accesslevelopenAccessfi
dc.relation.conferenceEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
dc.relation.grantnumber315550
dc.relation.grantnumber311877
dc.subject.ysokoneoppiminen
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p21846
dc.rights.urlhttp://rightsstatements.org/page/InC/1.0/?language=en
dc.relation.funderSuomen Akatemiafi
dc.relation.funderSuomen Akatemiafi
dc.relation.funderAcademy of Finlanden
dc.relation.funderAcademy of Finlanden
jyx.fundingprogramAkatemiaohjelma, SAfi
jyx.fundingprogramProfilointi, SAfi
jyx.fundingprogramAcademy Programme, AoFen
jyx.fundingprogramResearch profiles, AoFen
jyx.fundinginformationThe work of TK has been supported by the Academy of Finland from the projects 311877 (Demo) and 315550 (HNP-AI). The author gratefully acknowledge the role of ESANN in facilitating a collaborative platform with other active research groups of the two methods [11, 12].
dc.type.okmA4


Aineistoon kuuluvat tiedostot

Thumbnail

Aineisto kuuluu seuraaviin kokoelmiin

Näytä suppeat kuvailutiedot

In Copyright
Ellei muuten mainita, aineiston lisenssi on In Copyright