Statistical tests using hinge/ε-sensitive loss
| dc.authorid | 0000-0001-5838-4615 | |
| dc.authorid | 0000-0001-7506-0321 | |
| dc.contributor.author | Yıldız, Olcay Taner | en_US |
| dc.contributor.author | Alpaydın, Ahmet İbrahim Ethem | en_US |
| dc.date.accessioned | 2019-08-31T12:10:23Z | |
| dc.date.accessioned | 2019-08-05T16:04:56Z | |
| dc.date.available | 2019-08-31T12:10:23Z | |
| dc.date.available | 2019-08-05T16:04:56Z | |
| dc.date.issued | 2013 | |
| dc.department | Işık Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü | en_US |
| dc.department | Işık University, Faculty of Engineering, Department of Computer Engineering | en_US |
| dc.description.abstract | Statistical tests used in the literature to compare algorithms use the misclassification error which is based on the 0/1 loss and square loss for regression. Kernel-based, support vector machine classifiers (regressors) however are trained to minimize the hinge (ε-sensitive) loss and hence they should not be assessed or compared in terms of the 0/1 (square loss) but with the loss measure they are trained to minimize. We discuss how the paired t test can use the hinge (ε-sensitive) loss and show in our experiments that doing that, we can detect differences that the test on error cannot detect, indicating higher power in distinguishing between the behavior of kernel-based classifiers (regressors). Such tests can be generalized to compare L > 2 algorithms. | en_US |
| dc.description.version | Publisher's Version | en_US |
| dc.identifier.citation | Yıldız, O. T. & Alpaydın, A. İ. E. (2013). Statistical tests using hinge/ε-sensitive loss. Paper presented at the Computer and Information Sciences III - 27th International Symposium on Computer and Information Sciences, ISCIS 2012, 153-160. doi:10.1007/978-1-4471-4594-3-16 | en_US |
| dc.identifier.doi | 10.1007/978-1-4471-4594-3-16 | |
| dc.identifier.endpage | 160 | |
| dc.identifier.scopus | 2-s2.0-84887835903 | |
| dc.identifier.scopusquality | N/A | |
| dc.identifier.startpage | 153 | |
| dc.identifier.uri | https://hdl.handle.net/11729/1907 | |
| dc.identifier.uri | https://dx.doi.org/10.1007/978-1-4471-4594-3-16 | |
| dc.indekslendigikaynak | Scopus | en_US |
| dc.institutionauthor | Yıldız, Olcay Taner | en_US |
| dc.institutionauthorid | 0000-0001-5838-4615 | |
| dc.language.iso | en | en_US |
| dc.peerreviewed | Yes | en_US |
| dc.publicationstatus | Published | en_US |
| dc.publisher | Springer-Verlag | en_US |
| dc.relation.ispartof | Computer and Information Sciences III - 27th International Symposium on Computer and Information Sciences, ISCIS 2012 | en_US |
| dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
| dc.rights | info:eu-repo/semantics/closedAccess | en_US |
| dc.subject | Algorithms | en_US |
| dc.subject | Decision trees | en_US |
| dc.subject | Information science | en_US |
| dc.subject | Kernel based classifiers | en_US |
| dc.subject | Misclassification error | en_US |
| dc.subject | Neural networks | en_US |
| dc.subject | Statistical tests | en_US |
| dc.subject | Support vector machine classifiers | en_US |
| dc.subject | Support vector machines | en_US |
| dc.subject | T-tests | en_US |
| dc.title | Statistical tests using hinge/ε-sensitive loss | en_US |
| dc.type | Conference Object | en_US |
| dspace.entity.type | Publication |
Dosyalar
Orijinal paket
1 - 1 / 1
Küçük Resim Yok
- İsim:
- 1907.pdf
- Boyut:
- 280.36 KB
- Biçim:
- Adobe Portable Document Format
- Açıklama:
- Publisher's Version
