Back to Results List

Export

Link to this page

Please use this URL for citations.

Search Other Services

Statistics

  • Access to this page：1,401 times

＜departmental bulletin paper＞
Minimization Learning of Neural Networks by Adding Hidden Units

Creator
Creator Name
Niijima, Koichi
新島, 耕一
ニイジマ, コウイチ
Affiliation
Affiliation Name
Department of Informatics, Graduate School of Information Science and Electrical Engineering, Kyushu University
九州大学大学院システム情報科学研究科情報理学専攻
Creator Name
Yamada, Masaaki
ヤマダ, マサアキ
Affiliation
Affiliation Name
Department of Control Engineering and Science, Kyushu Institute of Technology : Graduate Student | NEC Corporation
Creator Name
Mohamed, Marghny H.
Affiliation
Affiliation Name
Department of Informatics, Graduate School of Information Science and Electrical Engineering, Kyushu University : Graduate Student
Creator Name
Akanuma, Taiga
アカヌマ, タイガ
Affiliation
Affiliation Name
Department of Informatics, Graduate School of Information Science and Electrical Engineering, Kyushu University : Graduate Student
Creator Name
Minamoto, Teruya
皆本, 晃弥
ミナモト, テルヤ
Affiliation
Affiliation Name
Department of Informatics, Graduate School of Information Science and Electrical Engineering, Kyushu University
九州大学大学院システム情報科学研究科情報理学専攻
Creator Name
Ohkubo, Akito
大久保, 彰人
オオクボ, アキト
Creator Alternative Name
Okubo, Akito
Affiliation
Affiliation Name
Fukuoka Institute of Health and Environmental Sciences
福岡県保健環境研究所
Language
English
Publisher
九州大学大学院システム情報科学研究科
Graduate School of Information Science and Electrical Engineering, Kyushu University
Date
1997-09-26
Source Title
Research reports on information science and electrical engineering of Kyushu University
Vol
2
Issue
2
First Page
173
Last Page
178
Publication Type
Version of Record
Access Rights
open access
JaLC DOI
https://doi.org/10.15017/1522387
Related DOI
https://portal.isee.kyushu-u.ac.jp/
Related URI
https://portal.isee.kyushu-u.ac.jp/
Relation
https://portal.isee.kyushu-u.ac.jp/
Abstract This paper proposes a minimization learning method for neural networks with one hidden layer. We treat two types of networks without and with thresholds in their output layers. Both of them are learnt... by minimizing error functions whenever one unit is added to the hidden layer. Our learning method is applied to design a neural network with thresholds for image recognition.show more

Hide fulltext details.

pdf p173 pdf 2.19 MB 191  

Details

PISSN
1342-3819
EISSN
2188-0891
NCID
AN10569524
Record ID
1522387
Peer-Reviewed
Refereed
Subject Terms
Minimization learning
Hidden unit
Threshold
Error function
Penalty method
Steepest descent method
Lagrange method
Created Date 2015.08.18
Modified Date 2020.12.15

People who viewed this item also viewed

Back to Results List