The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans l’apprentissage supervisé, l’une des principales méthodes d’apprentissage est l’apprentissage par mémorisation (ML). Puisqu’il réduit uniquement l’erreur d’entraînement, le ML ne garantit pas une bonne capacité de généralisation en général. Cependant, lorsque le ML est utilisé, l’acquisition d’une bonne capacité de généralisation est attendue. Cet usage du ML a été interprété par l'un des auteurs présents, H. Ogawa, comme un moyen de réaliser un « véritable apprentissage objectif » qui prend directement en compte la capacité de généralisation, et a introduit le concept de « véritable apprentissage objectif » qui prend directement en compte la capacité de généralisation. admissibilité. Si une méthode d’apprentissage peut offrir la même capacité de généralisation qu’un véritable apprentissage objectif, on dit que l’apprentissage objectif admet la méthode d’apprentissage. Par conséquent, si l’admissibilité n’est pas valable, il devient important de la faire valoir. Dans cet article, nous introduisons le concept de réalisation de la recevabilité, et concevoir une méthode de réalisation de l'admissibilité du BC en ce qui concerne apprentissage par projection qui prend directement en compte la capacité de généralisation.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Akira HIRABAYASHI, Hidemitsu OGAWA, Akiko NAKASHIMA, "Realization of Admissibility for Supervised Learning" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 5, pp. 1170-1176, May 2000, doi: .
Abstract: In supervised learning, one of the major learning methods is memorization learning (ML). Since it reduces only the training error, ML does not guarantee good generalization capability in general. When ML is used, however, acquiring good generalization capability is expected. This usage of ML was interpreted by one of the present authors, H. Ogawa, as a means of realizing 'true objective learning' which directly takes generalization capability into account, and introduced the concept of admissibility. If a learning method can provide the same generalization capability as a true objective learning, it is said that the objective learning admits the learning method. Hence, if admissibility does not hold, making it hold becomes important. In this paper, we introduce the concept of realization of admissibility, and devise a realization method of admissibility of ML with respect to projection learning which directly takes generalization capability into account.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_5_1170/_p
Copier
@ARTICLE{e83-d_5_1170,
author={Akira HIRABAYASHI, Hidemitsu OGAWA, Akiko NAKASHIMA, },
journal={IEICE TRANSACTIONS on Information},
title={Realization of Admissibility for Supervised Learning},
year={2000},
volume={E83-D},
number={5},
pages={1170-1176},
abstract={In supervised learning, one of the major learning methods is memorization learning (ML). Since it reduces only the training error, ML does not guarantee good generalization capability in general. When ML is used, however, acquiring good generalization capability is expected. This usage of ML was interpreted by one of the present authors, H. Ogawa, as a means of realizing 'true objective learning' which directly takes generalization capability into account, and introduced the concept of admissibility. If a learning method can provide the same generalization capability as a true objective learning, it is said that the objective learning admits the learning method. Hence, if admissibility does not hold, making it hold becomes important. In this paper, we introduce the concept of realization of admissibility, and devise a realization method of admissibility of ML with respect to projection learning which directly takes generalization capability into account.},
keywords={},
doi={},
ISSN={},
month={May},}
Copier
TY - JOUR
TI - Realization of Admissibility for Supervised Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1170
EP - 1176
AU - Akira HIRABAYASHI
AU - Hidemitsu OGAWA
AU - Akiko NAKASHIMA
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2000
AB - In supervised learning, one of the major learning methods is memorization learning (ML). Since it reduces only the training error, ML does not guarantee good generalization capability in general. When ML is used, however, acquiring good generalization capability is expected. This usage of ML was interpreted by one of the present authors, H. Ogawa, as a means of realizing 'true objective learning' which directly takes generalization capability into account, and introduced the concept of admissibility. If a learning method can provide the same generalization capability as a true objective learning, it is said that the objective learning admits the learning method. Hence, if admissibility does not hold, making it hold becomes important. In this paper, we introduce the concept of realization of admissibility, and devise a realization method of admissibility of ML with respect to projection learning which directly takes generalization capability into account.
ER -