Realization of Admissibility for Supervised Learning

Akira HIRABAYASHI; Hidemitsu OGAWA; Akiko NAKASHIMA

Realization of Admissibility for Supervised Learning

Akira HIRABAYASHI, Hidemitsu OGAWA, Akiko NAKASHIMA

Full Text Views

0

Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Information Vol.E83-D No.5 pp.1170-1176

Publication Date: 2000/05/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Biocybernetics, Neurocomputing

Cite this

Copy

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

Copy

@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},}

Copy

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 -