Nonlinear regression using second order methods

Simple item page
dc.citation.epage1088en_US
dc.citation.spage1085en_US
dc.contributor.authorCivek, Burak Cevaten_US
dc.contributor.authorDelibalta, İ.en_US
dc.contributor.authorKozat, Süleyman Serdaren_US
dc.coverage.spatialZonguldak, Turkeyen_US
dc.date.accessioned2018-04-12T11:48:38Z
dc.date.available2018-04-12T11:48:38Z
dc.date.issued2016en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 16-19 May 2016en_US
dc.descriptionConference Name: IEEE 24th Signal Processing and Communications Applications Conference, SIU 2016en_US
dc.description.abstractWe present a highly efficient algorithm for the online nonlinear regression problem. We process only the currently available data and do not reuse it, hence, there is no need for storage. For the nonlinear regression, we use piecewise linear modeling, where the regression space is partitioned into several regions and a linear model is fit to each region. As the first time in the literature, we use second order methods, e.g. Newton-Raphson Methods, and adaptively train both the region boundaries and the corresponding linear models. Therefore, we overcome the well known overfitting and underfitting problems. The proposed algorithm provides a substantial improvement in the performance compared to the state of the art.en_US
dc.identifier.doi10.1109/SIU.2016.7495932en_US
dc.identifier.urihttp://hdl.handle.net/11693/37707
dc.language.isoTurkishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/SIU.2016.7495932en_US
dc.source.titleProceedings of the IEEE 24th Signal Processing and Communications Applications Conference, SIU 2016en_US
dc.subjectNewtonen_US
dc.subjectNonlinear regressionen_US
dc.subjectPiecewise linear modelen_US
dc.titleNonlinear regression using second order methodsen_US
dc.title.alternativeİkinci dereceden metotlar kullanarak doğrusal olmayan bağlanımen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Nonlinear regression using second order methods [Ikinci Dereceden Metotlar Kullanarak Doǧrusal Olmayan Baǧlanim].pdf
Size:
634.39 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Electrical and Electronics Engineering