Comparision of Solutions of Numerical Gradient Descent Method and Continous Time Gradient Descent Dynamics and Lyapunov Stability

Basit Öğe Kaydı
dc.authoridYagmur, Nagihan/0000-0002-6407-4338
dc.authoridAlagoz, Baris Baykant/0000-0001-5238-6433
dc.authorwosidYagmur, Nagihan/JQI-3349-2023
dc.authorwosidAlagoz, Baris Baykant/ABG-8526-2020
dc.contributor.authorYagmur, Nagihan
dc.contributor.authorAlagoz, Baris Baykant
dc.date.accessioned2024-08-04T20:46:46Z
dc.date.available2024-08-04T20:46:46Z
dc.date.issued2019
dc.departmentİnönü Üniversitesien_US
dc.description27th Signal Processing and Communications Applications Conference (SIU) -- APR 24-26, 2019 -- Sivas Cumhuriyet Univ, Sivas, TURKEYen_US
dc.description.abstractGradient descent dynamics is an optimization techniques that is widely used in machine learning applications. This technique updates model parameter in the direction of descending of learning error. In this study, Lyapunov stability of continuous time gradient descent dynamics is investigated and robust stability condition, which is needed for implementation of gradient descent dynamics in intelligent control system applications, is evaluated. In a illustrative example, for a De Jong's function type error function, solutions of continuous gradient descent dynamics and Euler method based numerical solutions are compared and stability concerns is discussed.en_US
dc.description.sponsorshipIEEE Turkey Sect,Turkcell,Turkhavacilik Uzaysanayii,Turitak Bilgem,Gebze Teknik Univ,SAP, Detaysoft,NETAS,Havelsanen_US
dc.identifier.doi10.1109/siu.2019.8806396
dc.identifier.isbn978-1-7281-1904-5
dc.identifier.issn2165-0608
dc.identifier.scopus2-s2.0-85071992612en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://doi.org/10.1109/siu.2019.8806396
dc.identifier.urihttps://hdl.handle.net/11616/98947
dc.identifier.wosWOS:000518994300094en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isotren_US
dc.publisherIeeeen_US
dc.relation.ispartof2019 27th Signal Processing and Communications Applications Conference (Siu)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectgradient descent methoden_US
dc.subjectlearning dynamicsen_US
dc.subjectLyapunov stabilityen_US
dc.titleComparision of Solutions of Numerical Gradient Descent Method and Continous Time Gradient Descent Dynamics and Lyapunov Stabilityen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu