Presentation 1998/5/25
Improving the Generalization Ability of the Minimum Classification Error Learning and Its Application to Neural Networks
Jun ROKUI, Hiroshi SHIMODAIRA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The Minimum Classification Error (MCE) / Generalized Probabilistic Descent (GPD) learning proposed by Katagiri and Juang in 1992 has receive much attention because of its good recognition performance and wide range of applications including the case where the length of feature vectors is not fixed as in the case of speech recognition. In this report, we propose a new method to improve the generalization ability of the MCE learning by employing an regularization technique which is widely used to solve ill-posed problems. Feed-forward neural networks are employed to evaluate the performance of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) GPD / MCE / generalization / over-fitting / regularization
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1998/5/25(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Improving the Generalization Ability of the Minimum Classification Error Learning and Its Application to Neural Networks
Sub Title (in English)
Keyword(1) GPD
Keyword(2) MCE
Keyword(3) generalization
Keyword(4) over-fitting
Keyword(5) regularization
1st Author's Name Jun ROKUI
1st Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology()
2nd Author's Name Hiroshi SHIMODAIRA
2nd Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology
Date 1998/5/25
Paper #
Volume (vol) vol.98
Number (no) 77
Page pp.pp.-
#Pages 7
Date of Issue