Machine Learning Using Cellular Automata Based Feature Expansion and Reservoir Computing

Basit Öğe Kaydı
dc.contributor.authorYilmaz, Ozgur
dc.date.accessioned2025-10-24T18:10:20Z
dc.date.available2025-10-24T18:10:20Z
dc.date.issued2015
dc.departmentMalatya Turgut Özal Üniversitesi
dc.description.abstractIn this paper, we introduce a novel framework of cellular automata based computing that is capable of long short-term memory. Cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells and non-linear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the feature vector. The proposed framework requires orders of magnitude less computation compared to Echo State Networks. We prove that cellular automaton reservoir holds a distributed representation of attribute statistics, which provides a more effective computation than local representation. It is possible to estimate the kernel for linear cellular automata via metric learning, that enables a much more efficient distance computation in support vector machines framework.
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUBITAK) [114E554]; Turgut Ozal University BAP [006-10-2013]
dc.description.sponsorshipThis research is supported by The Scientific and Technological Research Council of Turkey (TUBITAK) Career Grant, No: 114E554 and Turgut Ozal University BAP Grant, No: 006-10-2013. I would like to thank Lenovo Group Ltd. Turkey Division, specifically Cagdas Ekinci and Alpay Erturkmen for their support in this research.
dc.identifier.endpage472
dc.identifier.issn1557-5969
dc.identifier.issn1557-5977
dc.identifier.issue5-6
dc.identifier.scopus2-s2.0-84945249528
dc.identifier.scopusqualityQ4
dc.identifier.startpage435
dc.identifier.urihttps://hdl.handle.net/20.500.12899/4112
dc.identifier.volume10
dc.identifier.wosWOS:000364606800006
dc.identifier.wosqualityQ4
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherOld City Publishing Inc
dc.relation.ispartofJournal Of Cellular Automata
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20251023
dc.subjectCellular automata; distributed representation; metric learning; kernel methods; reservoir computing
dc.titleMachine Learning Using Cellular Automata Based Feature Expansion and Reservoir Computing
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu