Associative learning method in a hypercolumn model

研究成果: ジャーナルへの寄稿記事

抄録

We propose an associatively learnable hypercolumn model (AHCM). A hyper-column model is a self-organized, competitive, and hierarchical multilayer neural network. It is derived from the neocognitron by replacing each S cell and C cell with a two-layer hierarchical self-organizing map. The HCM can recognize images with variant object size, position, orientation and spatial resolution. However, feature maps may integrate some features extracted in the lower layer even if the features are extracted from input data which belong to different categories. The learning algorithm of the HCM causes this problem because it is an unsupervised learning used by a self-organizing map. An associative learning method is therefore introduced, which is derived from the HCM by appending associative signals and associative weights to traditional input data and connection weights, respectively. The AHCM was applied to hand-shape recognition. We found that the AHCM could generate an appropriate feature map and higher recognition accuracy compared with the HCM.

元の言語英語
ページ(範囲)76-81
ページ数6
ジャーナルArtificial Life and Robotics
11
発行部数1
DOI
出版物ステータス出版済み - 1 1 2007

Fingerprint

Learning
Self organizing maps
Weights and Measures
Unsupervised learning
Multilayer neural networks
Hand
Learning algorithms
Recognition (Psychology)

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

これを引用

Associative learning method in a hypercolumn model. / Shimada, Atsushi; Tsuruta, Naoyuki; Taniguchi, Rin-Ichiro.

:: Artificial Life and Robotics, 巻 11, 番号 1, 01.01.2007, p. 76-81.

研究成果: ジャーナルへの寄稿記事

@article{415591daa2cf41e3b7baaaeb4389826e,
title = "Associative learning method in a hypercolumn model",
abstract = "We propose an associatively learnable hypercolumn model (AHCM). A hyper-column model is a self-organized, competitive, and hierarchical multilayer neural network. It is derived from the neocognitron by replacing each S cell and C cell with a two-layer hierarchical self-organizing map. The HCM can recognize images with variant object size, position, orientation and spatial resolution. However, feature maps may integrate some features extracted in the lower layer even if the features are extracted from input data which belong to different categories. The learning algorithm of the HCM causes this problem because it is an unsupervised learning used by a self-organizing map. An associative learning method is therefore introduced, which is derived from the HCM by appending associative signals and associative weights to traditional input data and connection weights, respectively. The AHCM was applied to hand-shape recognition. We found that the AHCM could generate an appropriate feature map and higher recognition accuracy compared with the HCM.",
author = "Atsushi Shimada and Naoyuki Tsuruta and Rin-Ichiro Taniguchi",
year = "2007",
month = "1",
day = "1",
doi = "10.1007/s10015-006-0404-x",
language = "English",
volume = "11",
pages = "76--81",
journal = "Artificial Life and Robotics",
issn = "1433-5298",
publisher = "Springer Japan",
number = "1",

}

TY - JOUR

T1 - Associative learning method in a hypercolumn model

AU - Shimada, Atsushi

AU - Tsuruta, Naoyuki

AU - Taniguchi, Rin-Ichiro

PY - 2007/1/1

Y1 - 2007/1/1

N2 - We propose an associatively learnable hypercolumn model (AHCM). A hyper-column model is a self-organized, competitive, and hierarchical multilayer neural network. It is derived from the neocognitron by replacing each S cell and C cell with a two-layer hierarchical self-organizing map. The HCM can recognize images with variant object size, position, orientation and spatial resolution. However, feature maps may integrate some features extracted in the lower layer even if the features are extracted from input data which belong to different categories. The learning algorithm of the HCM causes this problem because it is an unsupervised learning used by a self-organizing map. An associative learning method is therefore introduced, which is derived from the HCM by appending associative signals and associative weights to traditional input data and connection weights, respectively. The AHCM was applied to hand-shape recognition. We found that the AHCM could generate an appropriate feature map and higher recognition accuracy compared with the HCM.

AB - We propose an associatively learnable hypercolumn model (AHCM). A hyper-column model is a self-organized, competitive, and hierarchical multilayer neural network. It is derived from the neocognitron by replacing each S cell and C cell with a two-layer hierarchical self-organizing map. The HCM can recognize images with variant object size, position, orientation and spatial resolution. However, feature maps may integrate some features extracted in the lower layer even if the features are extracted from input data which belong to different categories. The learning algorithm of the HCM causes this problem because it is an unsupervised learning used by a self-organizing map. An associative learning method is therefore introduced, which is derived from the HCM by appending associative signals and associative weights to traditional input data and connection weights, respectively. The AHCM was applied to hand-shape recognition. We found that the AHCM could generate an appropriate feature map and higher recognition accuracy compared with the HCM.

UR - http://www.scopus.com/inward/record.url?scp=33846494290&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846494290&partnerID=8YFLogxK

U2 - 10.1007/s10015-006-0404-x

DO - 10.1007/s10015-006-0404-x

M3 - Article

VL - 11

SP - 76

EP - 81

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

SN - 1433-5298

IS - 1

ER -