Presentation 2020-03-17
Experimental Evaluation on Bayes Error Estimation Capability of Kernel Minimum Classification Error Training
Koji Yamada, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A pattern classifier incorporating kernel mapping, which is trained by the Kernel Minimum Classification Error (KMCE) training method, is shown to achieve the almost same high classification accuracy as an alternative kernel-mapping-based classifier, Support Vector Machine (SVM). However, previous evaluations for these classifiers were simply conducted in the Hold-Out scheme, and their results are not necessarily sufficient from the viewpoint of Bayes error estimation. In the paper, we compare them using four real-life datasets in the Cross-Validation scheme, and show that the KMCE-training-based classifier can accurately estimate the Bayes error with a much smaller classifier size than that of SVM.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Kernel Minimum Classification Error training / Kernel mapping / Support Vector Machine
Paper # PRMU2019-100
Date of Issue 2020-03-09 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2020/3/16(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT)
Secretary Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX)
Assistant Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Experimental Evaluation on Bayes Error Estimation Capability of Kernel Minimum Classification Error Training
Sub Title (in English)
Keyword(1) Kernel Minimum Classification Error training
Keyword(2) Kernel mapping
Keyword(3) Support Vector Machine
1st Author's Name Koji Yamada
1st Author's Affiliation Doshisha University(Doshisha Univ.)
2nd Author's Name Hideyuki Watanabe
2nd Author's Affiliation Advanced Telecommunications Research Institute International(ATR)
3rd Author's Name Shigeru Katagiri
3rd Author's Affiliation Doshisha University(Doshisha Univ.)
4th Author's Name Miho Ohsaki
4th Author's Affiliation Doshisha University(Doshisha Univ.)
Date 2020-03-17
Paper # PRMU2019-100
Volume (vol) vol.119
Number (no) PRMU-481
Page pp.pp.237-242(PRMU),
#Pages 6
Date of Issue 2020-03-09 (PRMU)