Vis enkel innførsel

dc.contributor.authorTunheim, Svein Anders
dc.contributor.authorYadav, Rohan Kumar
dc.contributor.authorLei, Jiao
dc.contributor.authorShafik, Rishad
dc.contributor.authorGranmo, Ole-Christoffer
dc.date.accessioned2023-05-11T09:53:20Z
dc.date.available2023-05-11T09:53:20Z
dc.date.created2022-10-09T15:23:18Z
dc.date.issued2022
dc.identifier.citationTunheim, Svein Anders Yadav, Rohan Kumar Lei, Jiao Shafik, Rishad Granmo, Ole-Christoffer (2022). Cyclostationary Random Number Sequences for the Tsetlin Machine. Lecture notes in Computer Science, 13343, 844-856.en_US
dc.identifier.isbn978-3-031-08529-1
dc.identifier.issn1611-3349
dc.identifier.urihttps://hdl.handle.net/11250/3067645
dc.descriptionAuthor's accepted manuscripten_US
dc.description.abstractThe Tsetlin Machine (TM) constitutes an emerging machine learning algorithm that has shown competitive performance on several benchmarks. The underlying concept of the TM is propositional logic determined by a group of finite state machines that learns patterns. Thus, TM-based systems naturally lend themselves to low-power operation when implemented in hardware for micro-edge Internet-of-Things applications. An important aspect of the learning phase of TMs is stochasticity. For low-power integrated circuit implementations the random number generation must be carried out efficiently. In this paper, we explore the application of pre-generated cyclostationary random number sequences for TMs. Through experiments on two machine learning problems, i.e., Binary Iris and Noisy XOR, we demonstrate that the accuracy is on par with standard TM. We show that through exploratory simulations the required length of the sequences that meets the conflicting tradeoffs can be suitably identified. Furthermore, the TMs achieve robust performance against reduced resolution of the random numbers. Finally, we show that maximum-length sequences implemented by linear feedback shift registers are suitable for generating the required random numbers.en_US
dc.language.isoengen_US
dc.publisherSpringer Nature Switzerland AGen_US
dc.relation.ispartofAdvances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence. 35th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2022, Kitakyushu, Japan, July 19–22, 2022, Proceedings
dc.relation.urihttps://link.springer.com/chapter/10.1007/978-3-031-08530-7_71#citeas
dc.titleCyclostationary Random Number Sequences for the Tsetlin Machineen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionacceptedVersionen_US
dc.rights.holder© 2022 Springer Nature Switzerland AGen_US
dc.subject.nsiVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550en_US
dc.source.pagenumber844-856en_US
dc.source.volume13343en_US
dc.source.journalLecture Notes in Computer Scienceen_US
dc.identifier.doihttps://doi.org/10.1007/978-3-031-08530-7_71
dc.identifier.cristin2059814
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel