Presentation 2019-12-06
Regularization Term of WRH Type Used with Moore-Penrose Inverse for Optimizing Neural Networks
Yoshifusa Ito, Hiroyuki Izumi, Cidambi Srinivasan,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Weigend et al. proposed an algorithm for optimizing neural networks, which suppressed the notorious over- tting. They attached a regularization term to the ordinary error cost function. In this paper, we use a regularization term of a similar type with the Moore-Penrose inverse for optimizing one-hidden-layer neural networks.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural networkBayesian Discriminant functionMoore-Penrose generalized inverseExtreme Learning MachinesWeight eliminationWRH-type
Paper # MBE2019-60,NC2019-51
Date of Issue 2019-11-29 (MBE, NC)

Conference Information
Committee NC / MBE
Conference Date 2019/12/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Toyohashi Tech
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hayaru Shouno(UEC) / Taishin Nomura(Osaka Univ.)
Vice Chair Kazuyuki Samejima(Tamagawa Univ) / Takashi Watanabe(Tohoku Univ.)
Secretary Kazuyuki Samejima(NAIST) / Takashi Watanabe(NTT)
Assistant Takashi Shinozaki(NICT) / Ken Takiyama(TUAT) / Yasuyuki Suzuki(Osaka Univ.) / Akihiro Karashima(Tohoku Inst. of Tech.)

Paper Information
Registration To Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Regularization Term of WRH Type Used with Moore-Penrose Inverse for Optimizing Neural Networks
Sub Title (in English)
Keyword(1) Neural networkBayesian Discriminant functionMoore-Penrose generalized inverseExtreme Learning MachinesWeight eliminationWRH-type
1st Author's Name Yoshifusa Ito
1st Author's Affiliation Fujita Health University(FHU)
2nd Author's Name Hiroyuki Izumi
2nd Author's Affiliation Aichi Gakuin University(AGU)
3rd Author's Name Cidambi Srinivasan
3rd Author's Affiliation University of Kentucky(UK)
Date 2019-12-06
Paper # MBE2019-60,NC2019-51
Volume (vol) vol.119
Number (no) MBE-327,NC-328
Page pp.pp.89-94(MBE), pp.89-94(NC),
#Pages 6
Date of Issue 2019-11-29 (MBE, NC)