Show simple item record

dc.contributor.authorLei, Jiao
dc.contributor.authorZhang, Xuan
dc.contributor.authorGranmo, Ole-Christoffer
dc.contributor.authorAbeyrathna, Kuruge Darshana
dc.date.accessioned2024-10-01T09:07:40Z
dc.date.available2024-10-01T09:07:40Z
dc.date.created2022-11-21T16:15:45Z
dc.date.issued2022
dc.identifier.citationLei, J., Zhang, X., Granmo, O.- C. & Abeyrathna, K. D. (2022). On the Convergence of Tsetlin Machines for the XOR Operator. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45 (5), 6072-6085.en_US
dc.identifier.issn0162-8828
dc.identifier.urihttps://hdl.handle.net/11250/3155327
dc.descriptionAuthor's Accepted Manuscript.en_US
dc.descriptionPersonal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
dc.description.abstractThe Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct properties, including transparent inference and learning using hardware-near building blocks. Although numerous papers explore the TM empirically, many of its properties have not yet been analyzed mathematically. In this article, we analyze the convergence of the TM when input is non-linearly related to output by the XOR-operator. Our analysis reveals that the TM, with just two conjunctive clauses, can converge almost surely to reproducing XOR, learning from training data over an infinite time horizon. Furthermore, the analysis shows how the hyper-parameter T guides clause construction so that the clauses capture the distinct sub-patterns in the data. Our analysis of convergence for XOR thus lays the foundation for analyzing other more complex logical expressions. These analyses altogether, from a mathematical perspective, provide new insights on why TMs have obtained the state-of-the-art performance on several pattern recognition problems.en_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.no*
dc.titleOn the Convergence of Tsetlin Machines for the XOR Operatoren_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionacceptedVersionen_US
dc.rights.holder© 2022 IEEEen_US
dc.subject.nsiVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550en_US
dc.source.pagenumber6072-6085en_US
dc.source.volume45en_US
dc.source.journalIEEE Transactions on Pattern Analysis and Machine Intelligenceen_US
dc.source.issue5en_US
dc.identifier.doihttps://doi.org/10.1109/TPAMI.2022.3203150
dc.identifier.cristin2077611
dc.relation.projectUniversitetet i Agder: CAIRen_US
cristin.ispublishedtrue
cristin.qualitycode1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal